Add files using upload-large-folder tool

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test1/README.md

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: transformers
+model_name: Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test1
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for Qwen3-14B-Base_productivity_splits_original_features_train_productivity_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/tjg90wvc) 
+
+
+
+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}
+}
+```

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/README.md

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: transformers
+model_name: Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for Qwen3-14B-Base_productivity_splits_original_features_train_productivity_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/3ulga1iu) 
+
+
+
+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}
+}
+```

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-1167/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

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-1167/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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.00237968804112545,
+  "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": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-1167/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 %}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-1167/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
+}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-1167/trainer_state.json

@@ -0,0 +1,297 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1167,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6110110306739807,
+      "epoch": 0.1287001287001287,
+      "grad_norm": 0.8611119389533997,
+      "learning_rate": 3.4130257962133866e-05,
+      "loss": 1.53956298828125,
+      "mean_token_accuracy": 0.6652342769503593,
+      "num_tokens": 73407.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.8662820833921433,
+      "epoch": 0.2574002574002574,
+      "grad_norm": 0.7405035495758057,
+      "learning_rate": 6.895705180104598e-05,
+      "loss": 0.7929539489746094,
+      "mean_token_accuracy": 0.7786347842216492,
+      "num_tokens": 143994.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7912819278240204,
+      "epoch": 0.3861003861003861,
+      "grad_norm": 0.6105485558509827,
+      "learning_rate": 0.00010378384563995809,
+      "loss": 0.7236511993408203,
+      "mean_token_accuracy": 0.7925467795133591,
+      "num_tokens": 216171.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.7777709531784057,
+      "epoch": 0.5148005148005148,
+      "grad_norm": 0.5781793594360352,
+      "learning_rate": 0.0001386106394788702,
+      "loss": 0.7024919891357422,
+      "mean_token_accuracy": 0.7969876372814179,
+      "num_tokens": 284702.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.7632609683275223,
+      "epoch": 0.6435006435006435,
+      "grad_norm": 0.6553444862365723,
+      "learning_rate": 0.00017343743331778232,
+      "loss": 0.7000718688964844,
+      "mean_token_accuracy": 0.7994742071628571,
+      "num_tokens": 356393.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.754165632724762,
+      "epoch": 0.7722007722007722,
+      "grad_norm": 0.634222149848938,
+      "learning_rate": 0.00020826422715669444,
+      "loss": 0.6909049987792969,
+      "mean_token_accuracy": 0.8016809666156769,
+      "num_tokens": 426916.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.7530711203813553,
+      "epoch": 0.9009009009009009,
+      "grad_norm": 0.7020156383514404,
+      "learning_rate": 0.00024309102099560653,
+      "loss": 0.69554931640625,
+      "mean_token_accuracy": 0.8002807641029358,
+      "num_tokens": 499603.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.5728044164242204,
+      "eval_loss": 0.6785851716995239,
+      "eval_mean_token_accuracy": 0.798433246993527,
+      "eval_num_tokens": 555493.0,
+      "eval_runtime": 162.4129,
+      "eval_samples_per_second": 9.513,
+      "eval_steps_per_second": 1.194,
+      "step": 389
+    },
+    {
+      "entropy": 0.7489313946829902,
+      "epoch": 1.0283140283140284,
+      "grad_norm": 0.7532815933227539,
+      "learning_rate": 0.0002709470016827303,
+      "loss": 0.6856581878662109,
+      "mean_token_accuracy": 0.8023027079273956,
+      "num_tokens": 570813.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.7238409864902496,
+      "epoch": 1.157014157014157,
+      "grad_norm": 1.2016215324401855,
+      "learning_rate": 0.0002707561443541359,
+      "loss": 0.6699818420410156,
+      "mean_token_accuracy": 0.8070302194356919,
+      "num_tokens": 642956.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.7388938587903976,
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.7279272079467773,
+      "learning_rate": 0.0002702930068622498,
+      "loss": 0.6728517150878907,
+      "mean_token_accuracy": 0.8049580943584442,
+      "num_tokens": 714498.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.7284485149383545,
+      "epoch": 1.4144144144144144,
+      "grad_norm": 0.8563987016677856,
+      "learning_rate": 0.0002695585213716931,
+      "loss": 0.6657986450195312,
+      "mean_token_accuracy": 0.8085588800907135,
+      "num_tokens": 785595.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.6960959500074386,
+      "epoch": 1.5431145431145432,
+      "grad_norm": 0.5145474672317505,
+      "learning_rate": 0.0002685541661937683,
+      "loss": 0.6358638763427734,
+      "mean_token_accuracy": 0.8131621342897415,
+      "num_tokens": 857551.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.7220414417982102,
+      "epoch": 1.6718146718146718,
+      "grad_norm": 0.9381059408187866,
+      "learning_rate": 0.00026728196281103746,
+      "loss": 0.6531407928466797,
+      "mean_token_accuracy": 0.811619822382927,
+      "num_tokens": 926864.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.6955459499359131,
+      "epoch": 1.8005148005148004,
+      "grad_norm": 0.6115108728408813,
+      "learning_rate": 0.0002657444718086503,
+      "loss": 0.6269588088989257,
+      "mean_token_accuracy": 0.8155373805761337,
+      "num_tokens": 998824.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.6929812705516816,
+      "epoch": 1.9292149292149292,
+      "grad_norm": 0.749489426612854,
+      "learning_rate": 0.0002639447877206115,
+      "loss": 0.629054069519043,
+      "mean_token_accuracy": 0.8183021235466004,
+      "num_tokens": 1069332.0,
+      "step": 750
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.5833694102223387,
+      "eval_loss": 0.6328718662261963,
+      "eval_mean_token_accuracy": 0.8159044071571114,
+      "eval_num_tokens": 1110986.0,
+      "eval_runtime": 161.885,
+      "eval_samples_per_second": 9.544,
+      "eval_steps_per_second": 1.198,
+      "step": 778
+    },
+    {
+      "entropy": 0.647241060480927,
+      "epoch": 2.056628056628057,
+      "grad_norm": 0.7070767879486084,
+      "learning_rate": 0.00026188653280135975,
+      "loss": 0.5823922348022461,
+      "mean_token_accuracy": 0.8265365301960647,
+      "num_tokens": 1141195.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5995378407835961,
+      "epoch": 2.1853281853281854,
+      "grad_norm": 0.8090486526489258,
+      "learning_rate": 0.0002595738497351955,
+      "loss": 0.5325597763061524,
+      "mean_token_accuracy": 0.8369336777925491,
+      "num_tokens": 1210708.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.6043145382404327,
+      "epoch": 2.314028314028314,
+      "grad_norm": 0.8279913067817688,
+      "learning_rate": 0.00025701139329823054,
+      "loss": 0.5414446258544922,
+      "mean_token_accuracy": 0.8361396533250809,
+      "num_tokens": 1283441.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.5953224584460258,
+      "epoch": 2.4427284427284426,
+      "grad_norm": 0.6075023412704468,
+      "learning_rate": 0.00025420432098964183,
+      "loss": 0.536654167175293,
+      "mean_token_accuracy": 0.8340093129873276,
+      "num_tokens": 1356418.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.5998479858040809,
+      "epoch": 2.571428571428571,
+      "grad_norm": 1.0311471223831177,
+      "learning_rate": 0.0002511582826510862,
+      "loss": 0.5372924423217773,
+      "mean_token_accuracy": 0.8366045409440994,
+      "num_tokens": 1427797.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.5980158120393753,
+      "epoch": 2.7001287001287,
+      "grad_norm": 0.5971426367759705,
+      "learning_rate": 0.0002478794090951689,
+      "loss": 0.5392885208129883,
+      "mean_token_accuracy": 0.8347727072238922,
+      "num_tokens": 1498082.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.5990680930018425,
+      "epoch": 2.828828828828829,
+      "grad_norm": 0.5662627220153809,
+      "learning_rate": 0.0002443742997658538,
+      "loss": 0.5360498428344727,
+      "mean_token_accuracy": 0.8371847170591354,
+      "num_tokens": 1568798.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.5957039377093315,
+      "epoch": 2.9575289575289574,
+      "grad_norm": 0.5043798685073853,
+      "learning_rate": 0.00024065000945565205,
+      "loss": 0.5342231369018555,
+      "mean_token_accuracy": 0.8380735236406326,
+      "num_tokens": 1643449.0,
+      "step": 1150
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.5346978819861854,
+      "eval_loss": 0.6255015134811401,
+      "eval_mean_token_accuracy": 0.8202014476368108,
+      "eval_num_tokens": 1666479.0,
+      "eval_runtime": 161.6098,
+      "eval_samples_per_second": 9.56,
+      "eval_steps_per_second": 1.2,
+      "step": 1167
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3890,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.7917443648582656e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-1556/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

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-1556/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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.00237968804112545,
+  "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": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-1556/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 %}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-1556/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
+}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-1556/trainer_state.json

@@ -0,0 +1,388 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1556,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6110110306739807,
+      "epoch": 0.1287001287001287,
+      "grad_norm": 0.8611119389533997,
+      "learning_rate": 3.4130257962133866e-05,
+      "loss": 1.53956298828125,
+      "mean_token_accuracy": 0.6652342769503593,
+      "num_tokens": 73407.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.8662820833921433,
+      "epoch": 0.2574002574002574,
+      "grad_norm": 0.7405035495758057,
+      "learning_rate": 6.895705180104598e-05,
+      "loss": 0.7929539489746094,
+      "mean_token_accuracy": 0.7786347842216492,
+      "num_tokens": 143994.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7912819278240204,
+      "epoch": 0.3861003861003861,
+      "grad_norm": 0.6105485558509827,
+      "learning_rate": 0.00010378384563995809,
+      "loss": 0.7236511993408203,
+      "mean_token_accuracy": 0.7925467795133591,
+      "num_tokens": 216171.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.7777709531784057,
+      "epoch": 0.5148005148005148,
+      "grad_norm": 0.5781793594360352,
+      "learning_rate": 0.0001386106394788702,
+      "loss": 0.7024919891357422,
+      "mean_token_accuracy": 0.7969876372814179,
+      "num_tokens": 284702.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.7632609683275223,
+      "epoch": 0.6435006435006435,
+      "grad_norm": 0.6553444862365723,
+      "learning_rate": 0.00017343743331778232,
+      "loss": 0.7000718688964844,
+      "mean_token_accuracy": 0.7994742071628571,
+      "num_tokens": 356393.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.754165632724762,
+      "epoch": 0.7722007722007722,
+      "grad_norm": 0.634222149848938,
+      "learning_rate": 0.00020826422715669444,
+      "loss": 0.6909049987792969,
+      "mean_token_accuracy": 0.8016809666156769,
+      "num_tokens": 426916.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.7530711203813553,
+      "epoch": 0.9009009009009009,
+      "grad_norm": 0.7020156383514404,
+      "learning_rate": 0.00024309102099560653,
+      "loss": 0.69554931640625,
+      "mean_token_accuracy": 0.8002807641029358,
+      "num_tokens": 499603.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.5728044164242204,
+      "eval_loss": 0.6785851716995239,
+      "eval_mean_token_accuracy": 0.798433246993527,
+      "eval_num_tokens": 555493.0,
+      "eval_runtime": 162.4129,
+      "eval_samples_per_second": 9.513,
+      "eval_steps_per_second": 1.194,
+      "step": 389
+    },
+    {
+      "entropy": 0.7489313946829902,
+      "epoch": 1.0283140283140284,
+      "grad_norm": 0.7532815933227539,
+      "learning_rate": 0.0002709470016827303,
+      "loss": 0.6856581878662109,
+      "mean_token_accuracy": 0.8023027079273956,
+      "num_tokens": 570813.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.7238409864902496,
+      "epoch": 1.157014157014157,
+      "grad_norm": 1.2016215324401855,
+      "learning_rate": 0.0002707561443541359,
+      "loss": 0.6699818420410156,
+      "mean_token_accuracy": 0.8070302194356919,
+      "num_tokens": 642956.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.7388938587903976,
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.7279272079467773,
+      "learning_rate": 0.0002702930068622498,
+      "loss": 0.6728517150878907,
+      "mean_token_accuracy": 0.8049580943584442,
+      "num_tokens": 714498.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.7284485149383545,
+      "epoch": 1.4144144144144144,
+      "grad_norm": 0.8563987016677856,
+      "learning_rate": 0.0002695585213716931,
+      "loss": 0.6657986450195312,
+      "mean_token_accuracy": 0.8085588800907135,
+      "num_tokens": 785595.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.6960959500074386,
+      "epoch": 1.5431145431145432,
+      "grad_norm": 0.5145474672317505,
+      "learning_rate": 0.0002685541661937683,
+      "loss": 0.6358638763427734,
+      "mean_token_accuracy": 0.8131621342897415,
+      "num_tokens": 857551.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.7220414417982102,
+      "epoch": 1.6718146718146718,
+      "grad_norm": 0.9381059408187866,
+      "learning_rate": 0.00026728196281103746,
+      "loss": 0.6531407928466797,
+      "mean_token_accuracy": 0.811619822382927,
+      "num_tokens": 926864.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.6955459499359131,
+      "epoch": 1.8005148005148004,
+      "grad_norm": 0.6115108728408813,
+      "learning_rate": 0.0002657444718086503,
+      "loss": 0.6269588088989257,
+      "mean_token_accuracy": 0.8155373805761337,
+      "num_tokens": 998824.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.6929812705516816,
+      "epoch": 1.9292149292149292,
+      "grad_norm": 0.749489426612854,
+      "learning_rate": 0.0002639447877206115,
+      "loss": 0.629054069519043,
+      "mean_token_accuracy": 0.8183021235466004,
+      "num_tokens": 1069332.0,
+      "step": 750
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.5833694102223387,
+      "eval_loss": 0.6328718662261963,
+      "eval_mean_token_accuracy": 0.8159044071571114,
+      "eval_num_tokens": 1110986.0,
+      "eval_runtime": 161.885,
+      "eval_samples_per_second": 9.544,
+      "eval_steps_per_second": 1.198,
+      "step": 778
+    },
+    {
+      "entropy": 0.647241060480927,
+      "epoch": 2.056628056628057,
+      "grad_norm": 0.7070767879486084,
+      "learning_rate": 0.00026188653280135975,
+      "loss": 0.5823922348022461,
+      "mean_token_accuracy": 0.8265365301960647,
+      "num_tokens": 1141195.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5995378407835961,
+      "epoch": 2.1853281853281854,
+      "grad_norm": 0.8090486526489258,
+      "learning_rate": 0.0002595738497351955,
+      "loss": 0.5325597763061524,
+      "mean_token_accuracy": 0.8369336777925491,
+      "num_tokens": 1210708.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.6043145382404327,
+      "epoch": 2.314028314028314,
+      "grad_norm": 0.8279913067817688,
+      "learning_rate": 0.00025701139329823054,
+      "loss": 0.5414446258544922,
+      "mean_token_accuracy": 0.8361396533250809,
+      "num_tokens": 1283441.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.5953224584460258,
+      "epoch": 2.4427284427284426,
+      "grad_norm": 0.6075023412704468,
+      "learning_rate": 0.00025420432098964183,
+      "loss": 0.536654167175293,
+      "mean_token_accuracy": 0.8340093129873276,
+      "num_tokens": 1356418.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.5998479858040809,
+      "epoch": 2.571428571428571,
+      "grad_norm": 1.0311471223831177,
+      "learning_rate": 0.0002511582826510862,
+      "loss": 0.5372924423217773,
+      "mean_token_accuracy": 0.8366045409440994,
+      "num_tokens": 1427797.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.5980158120393753,
+      "epoch": 2.7001287001287,
+      "grad_norm": 0.5971426367759705,
+      "learning_rate": 0.0002478794090951689,
+      "loss": 0.5392885208129883,
+      "mean_token_accuracy": 0.8347727072238922,
+      "num_tokens": 1498082.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.5990680930018425,
+      "epoch": 2.828828828828829,
+      "grad_norm": 0.5662627220153809,
+      "learning_rate": 0.0002443742997658538,
+      "loss": 0.5360498428344727,
+      "mean_token_accuracy": 0.8371847170591354,
+      "num_tokens": 1568798.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.5957039377093315,
+      "epoch": 2.9575289575289574,
+      "grad_norm": 0.5043798685073853,
+      "learning_rate": 0.00024065000945565205,
+      "loss": 0.5342231369018555,
+      "mean_token_accuracy": 0.8380735236406326,
+      "num_tokens": 1643449.0,
+      "step": 1150
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.5346978819861854,
+      "eval_loss": 0.6255015134811401,
+      "eval_mean_token_accuracy": 0.8202014476368108,
+      "eval_num_tokens": 1666479.0,
+      "eval_runtime": 161.6098,
+      "eval_samples_per_second": 9.56,
+      "eval_steps_per_second": 1.2,
+      "step": 1167
+    },
+    {
+      "entropy": 0.5212209137401196,
+      "epoch": 3.0849420849420848,
+      "grad_norm": 0.7095440626144409,
+      "learning_rate": 0.00023671403410632178,
+      "loss": 0.45311901092529294,
+      "mean_token_accuracy": 0.856362871449403,
+      "num_tokens": 1713536.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.4701593083143234,
+      "epoch": 3.213642213642214,
+      "grad_norm": 0.6408083438873291,
+      "learning_rate": 0.0002325742957216607,
+      "loss": 0.39916397094726563,
+      "mean_token_accuracy": 0.8698061722517013,
+      "num_tokens": 1785609.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.4766591975092888,
+      "epoch": 3.3423423423423424,
+      "grad_norm": 0.6415093541145325,
+      "learning_rate": 0.0002282391264227552,
+      "loss": 0.4116698455810547,
+      "mean_token_accuracy": 0.8679435575008392,
+      "num_tokens": 1858651.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.4937947469949722,
+      "epoch": 3.471042471042471,
+      "grad_norm": 0.6549825072288513,
+      "learning_rate": 0.00022371725167778054,
+      "loss": 0.4296376037597656,
+      "mean_token_accuracy": 0.8609357953071595,
+      "num_tokens": 1928692.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.4920153194665909,
+      "epoch": 3.5997425997425996,
+      "grad_norm": 0.6452126502990723,
+      "learning_rate": 0.00021901777274010406,
+      "loss": 0.4307489013671875,
+      "mean_token_accuracy": 0.8606827831268311,
+      "num_tokens": 1998668.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.490042342543602,
+      "epoch": 3.7284427284427286,
+      "grad_norm": 0.5727734565734863,
+      "learning_rate": 0.0002141501483300395,
+      "loss": 0.4295254135131836,
+      "mean_token_accuracy": 0.8616545403003693,
+      "num_tokens": 2072809.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.49857193052768706,
+      "epoch": 3.857142857142857,
+      "grad_norm": 0.7732954025268555,
+      "learning_rate": 0.00020912417559712133,
+      "loss": 0.4289303207397461,
+      "mean_token_accuracy": 0.8616443765163422,
+      "num_tokens": 2142475.0,
+      "step": 1500
+    },
+    {
+      "entropy": 0.4746784272789955,
+      "epoch": 3.985842985842986,
+      "grad_norm": 0.5791187882423401,
+      "learning_rate": 0.00020394997040121726,
+      "loss": 0.4180263900756836,
+      "mean_token_accuracy": 0.866080379486084,
+      "num_tokens": 2214044.0,
+      "step": 1550
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.4793926059585257,
+      "eval_loss": 0.627627968788147,
+      "eval_mean_token_accuracy": 0.8233870095813397,
+      "eval_num_tokens": 2221972.0,
+      "eval_runtime": 162.0225,
+      "eval_samples_per_second": 9.536,
+      "eval_steps_per_second": 1.197,
+      "step": 1556
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3890,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.723284547240653e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-1945/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

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-1945/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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.00237968804112545,
+  "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": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-1945/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 %}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-1945/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
+}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-1945/trainer_state.json

@@ -0,0 +1,469 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1945,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6110110306739807,
+      "epoch": 0.1287001287001287,
+      "grad_norm": 0.8611119389533997,
+      "learning_rate": 3.4130257962133866e-05,
+      "loss": 1.53956298828125,
+      "mean_token_accuracy": 0.6652342769503593,
+      "num_tokens": 73407.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.8662820833921433,
+      "epoch": 0.2574002574002574,
+      "grad_norm": 0.7405035495758057,
+      "learning_rate": 6.895705180104598e-05,
+      "loss": 0.7929539489746094,
+      "mean_token_accuracy": 0.7786347842216492,
+      "num_tokens": 143994.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7912819278240204,
+      "epoch": 0.3861003861003861,
+      "grad_norm": 0.6105485558509827,
+      "learning_rate": 0.00010378384563995809,
+      "loss": 0.7236511993408203,
+      "mean_token_accuracy": 0.7925467795133591,
+      "num_tokens": 216171.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.7777709531784057,
+      "epoch": 0.5148005148005148,
+      "grad_norm": 0.5781793594360352,
+      "learning_rate": 0.0001386106394788702,
+      "loss": 0.7024919891357422,
+      "mean_token_accuracy": 0.7969876372814179,
+      "num_tokens": 284702.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.7632609683275223,
+      "epoch": 0.6435006435006435,
+      "grad_norm": 0.6553444862365723,
+      "learning_rate": 0.00017343743331778232,
+      "loss": 0.7000718688964844,
+      "mean_token_accuracy": 0.7994742071628571,
+      "num_tokens": 356393.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.754165632724762,
+      "epoch": 0.7722007722007722,
+      "grad_norm": 0.634222149848938,
+      "learning_rate": 0.00020826422715669444,
+      "loss": 0.6909049987792969,
+      "mean_token_accuracy": 0.8016809666156769,
+      "num_tokens": 426916.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.7530711203813553,
+      "epoch": 0.9009009009009009,
+      "grad_norm": 0.7020156383514404,
+      "learning_rate": 0.00024309102099560653,
+      "loss": 0.69554931640625,
+      "mean_token_accuracy": 0.8002807641029358,
+      "num_tokens": 499603.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.5728044164242204,
+      "eval_loss": 0.6785851716995239,
+      "eval_mean_token_accuracy": 0.798433246993527,
+      "eval_num_tokens": 555493.0,
+      "eval_runtime": 162.4129,
+      "eval_samples_per_second": 9.513,
+      "eval_steps_per_second": 1.194,
+      "step": 389
+    },
+    {
+      "entropy": 0.7489313946829902,
+      "epoch": 1.0283140283140284,
+      "grad_norm": 0.7532815933227539,
+      "learning_rate": 0.0002709470016827303,
+      "loss": 0.6856581878662109,
+      "mean_token_accuracy": 0.8023027079273956,
+      "num_tokens": 570813.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.7238409864902496,
+      "epoch": 1.157014157014157,
+      "grad_norm": 1.2016215324401855,
+      "learning_rate": 0.0002707561443541359,
+      "loss": 0.6699818420410156,
+      "mean_token_accuracy": 0.8070302194356919,
+      "num_tokens": 642956.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.7388938587903976,
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.7279272079467773,
+      "learning_rate": 0.0002702930068622498,
+      "loss": 0.6728517150878907,
+      "mean_token_accuracy": 0.8049580943584442,
+      "num_tokens": 714498.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.7284485149383545,
+      "epoch": 1.4144144144144144,
+      "grad_norm": 0.8563987016677856,
+      "learning_rate": 0.0002695585213716931,
+      "loss": 0.6657986450195312,
+      "mean_token_accuracy": 0.8085588800907135,
+      "num_tokens": 785595.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.6960959500074386,
+      "epoch": 1.5431145431145432,
+      "grad_norm": 0.5145474672317505,
+      "learning_rate": 0.0002685541661937683,
+      "loss": 0.6358638763427734,
+      "mean_token_accuracy": 0.8131621342897415,
+      "num_tokens": 857551.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.7220414417982102,
+      "epoch": 1.6718146718146718,
+      "grad_norm": 0.9381059408187866,
+      "learning_rate": 0.00026728196281103746,
+      "loss": 0.6531407928466797,
+      "mean_token_accuracy": 0.811619822382927,
+      "num_tokens": 926864.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.6955459499359131,
+      "epoch": 1.8005148005148004,
+      "grad_norm": 0.6115108728408813,
+      "learning_rate": 0.0002657444718086503,
+      "loss": 0.6269588088989257,
+      "mean_token_accuracy": 0.8155373805761337,
+      "num_tokens": 998824.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.6929812705516816,
+      "epoch": 1.9292149292149292,
+      "grad_norm": 0.749489426612854,
+      "learning_rate": 0.0002639447877206115,
+      "loss": 0.629054069519043,
+      "mean_token_accuracy": 0.8183021235466004,
+      "num_tokens": 1069332.0,
+      "step": 750
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.5833694102223387,
+      "eval_loss": 0.6328718662261963,
+      "eval_mean_token_accuracy": 0.8159044071571114,
+      "eval_num_tokens": 1110986.0,
+      "eval_runtime": 161.885,
+      "eval_samples_per_second": 9.544,
+      "eval_steps_per_second": 1.198,
+      "step": 778
+    },
+    {
+      "entropy": 0.647241060480927,
+      "epoch": 2.056628056628057,
+      "grad_norm": 0.7070767879486084,
+      "learning_rate": 0.00026188653280135975,
+      "loss": 0.5823922348022461,
+      "mean_token_accuracy": 0.8265365301960647,
+      "num_tokens": 1141195.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5995378407835961,
+      "epoch": 2.1853281853281854,
+      "grad_norm": 0.8090486526489258,
+      "learning_rate": 0.0002595738497351955,
+      "loss": 0.5325597763061524,
+      "mean_token_accuracy": 0.8369336777925491,
+      "num_tokens": 1210708.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.6043145382404327,
+      "epoch": 2.314028314028314,
+      "grad_norm": 0.8279913067817688,
+      "learning_rate": 0.00025701139329823054,
+      "loss": 0.5414446258544922,
+      "mean_token_accuracy": 0.8361396533250809,
+      "num_tokens": 1283441.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.5953224584460258,
+      "epoch": 2.4427284427284426,
+      "grad_norm": 0.6075023412704468,
+      "learning_rate": 0.00025420432098964183,
+      "loss": 0.536654167175293,
+      "mean_token_accuracy": 0.8340093129873276,
+      "num_tokens": 1356418.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.5998479858040809,
+      "epoch": 2.571428571428571,
+      "grad_norm": 1.0311471223831177,
+      "learning_rate": 0.0002511582826510862,
+      "loss": 0.5372924423217773,
+      "mean_token_accuracy": 0.8366045409440994,
+      "num_tokens": 1427797.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.5980158120393753,
+      "epoch": 2.7001287001287,
+      "grad_norm": 0.5971426367759705,
+      "learning_rate": 0.0002478794090951689,
+      "loss": 0.5392885208129883,
+      "mean_token_accuracy": 0.8347727072238922,
+      "num_tokens": 1498082.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.5990680930018425,
+      "epoch": 2.828828828828829,
+      "grad_norm": 0.5662627220153809,
+      "learning_rate": 0.0002443742997658538,
+      "loss": 0.5360498428344727,
+      "mean_token_accuracy": 0.8371847170591354,
+      "num_tokens": 1568798.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.5957039377093315,
+      "epoch": 2.9575289575289574,
+      "grad_norm": 0.5043798685073853,
+      "learning_rate": 0.00024065000945565205,
+      "loss": 0.5342231369018555,
+      "mean_token_accuracy": 0.8380735236406326,
+      "num_tokens": 1643449.0,
+      "step": 1150
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.5346978819861854,
+      "eval_loss": 0.6255015134811401,
+      "eval_mean_token_accuracy": 0.8202014476368108,
+      "eval_num_tokens": 1666479.0,
+      "eval_runtime": 161.6098,
+      "eval_samples_per_second": 9.56,
+      "eval_steps_per_second": 1.2,
+      "step": 1167
+    },
+    {
+      "entropy": 0.5212209137401196,
+      "epoch": 3.0849420849420848,
+      "grad_norm": 0.7095440626144409,
+      "learning_rate": 0.00023671403410632178,
+      "loss": 0.45311901092529294,
+      "mean_token_accuracy": 0.856362871449403,
+      "num_tokens": 1713536.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.4701593083143234,
+      "epoch": 3.213642213642214,
+      "grad_norm": 0.6408083438873291,
+      "learning_rate": 0.0002325742957216607,
+      "loss": 0.39916397094726563,
+      "mean_token_accuracy": 0.8698061722517013,
+      "num_tokens": 1785609.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.4766591975092888,
+      "epoch": 3.3423423423423424,
+      "grad_norm": 0.6415093541145325,
+      "learning_rate": 0.0002282391264227552,
+      "loss": 0.4116698455810547,
+      "mean_token_accuracy": 0.8679435575008392,
+      "num_tokens": 1858651.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.4937947469949722,
+      "epoch": 3.471042471042471,
+      "grad_norm": 0.6549825072288513,
+      "learning_rate": 0.00022371725167778054,
+      "loss": 0.4296376037597656,
+      "mean_token_accuracy": 0.8609357953071595,
+      "num_tokens": 1928692.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.4920153194665909,
+      "epoch": 3.5997425997425996,
+      "grad_norm": 0.6452126502990723,
+      "learning_rate": 0.00021901777274010406,
+      "loss": 0.4307489013671875,
+      "mean_token_accuracy": 0.8606827831268311,
+      "num_tokens": 1998668.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.490042342543602,
+      "epoch": 3.7284427284427286,
+      "grad_norm": 0.5727734565734863,
+      "learning_rate": 0.0002141501483300395,
+      "loss": 0.4295254135131836,
+      "mean_token_accuracy": 0.8616545403003693,
+      "num_tokens": 2072809.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.49857193052768706,
+      "epoch": 3.857142857142857,
+      "grad_norm": 0.7732954025268555,
+      "learning_rate": 0.00020912417559712133,
+      "loss": 0.4289303207397461,
+      "mean_token_accuracy": 0.8616443765163422,
+      "num_tokens": 2142475.0,
+      "step": 1500
+    },
+    {
+      "entropy": 0.4746784272789955,
+      "epoch": 3.985842985842986,
+      "grad_norm": 0.5791187882423401,
+      "learning_rate": 0.00020394997040121726,
+      "loss": 0.4180263900756836,
+      "mean_token_accuracy": 0.866080379486084,
+      "num_tokens": 2214044.0,
+      "step": 1550
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.4793926059585257,
+      "eval_loss": 0.627627968788147,
+      "eval_mean_token_accuracy": 0.8233870095813397,
+      "eval_num_tokens": 2221972.0,
+      "eval_runtime": 162.0225,
+      "eval_samples_per_second": 9.536,
+      "eval_steps_per_second": 1.197,
+      "step": 1556
+    },
+    {
+      "entropy": 0.38195489000792454,
+      "epoch": 4.113256113256114,
+      "grad_norm": 0.6002617478370667,
+      "learning_rate": 0.0001986379469521669,
+      "loss": 0.30819049835205076,
+      "mean_token_accuracy": 0.8977848634575353,
+      "num_tokens": 2282164.0,
+      "step": 1600
+    },
+    {
+      "entropy": 0.3655787402391434,
+      "epoch": 4.241956241956242,
+      "grad_norm": 0.7100041508674622,
+      "learning_rate": 0.00019319879684892634,
+      "loss": 0.29959835052490236,
+      "mean_token_accuracy": 0.8991208010911942,
+      "num_tokens": 2353213.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.3821141055226326,
+      "epoch": 4.370656370656371,
+      "grad_norm": 0.5848307013511658,
+      "learning_rate": 0.00018764346756040715,
+      "loss": 0.313802490234375,
+      "mean_token_accuracy": 0.895167955160141,
+      "num_tokens": 2425068.0,
+      "step": 1700
+    },
+    {
+      "entropy": 0.37083797007799146,
+      "epoch": 4.499356499356499,
+      "grad_norm": 0.6447024941444397,
+      "learning_rate": 0.00018198314039132143,
+      "loss": 0.30583988189697264,
+      "mean_token_accuracy": 0.8961733293533325,
+      "num_tokens": 2498321.0,
+      "step": 1750
+    },
+    {
+      "entropy": 0.3791545969247818,
+      "epoch": 4.628056628056628,
+      "grad_norm": 0.6575382351875305,
+      "learning_rate": 0.00017622920797738184,
+      "loss": 0.3088031005859375,
+      "mean_token_accuracy": 0.8960050916671753,
+      "num_tokens": 2570321.0,
+      "step": 1800
+    },
+    {
+      "entropy": 0.3946831756830215,
+      "epoch": 4.756756756756757,
+      "grad_norm": 0.5351552963256836,
+      "learning_rate": 0.00017039325135515207,
+      "loss": 0.3229162979125977,
+      "mean_token_accuracy": 0.8920552498102188,
+      "num_tokens": 2642851.0,
+      "step": 1850
+    },
+    {
+      "entropy": 0.37298239797353744,
+      "epoch": 4.885456885456885,
+      "grad_norm": 0.7624587416648865,
+      "learning_rate": 0.00016448701665269964,
+      "loss": 0.3067934799194336,
+      "mean_token_accuracy": 0.8951873427629471,
+      "num_tokens": 2715629.0,
+      "step": 1900
+    },
+    {
+      "epoch": 5.0,
+      "eval_entropy": 0.3738150204887095,
+      "eval_loss": 0.7131896615028381,
+      "eval_mean_token_accuracy": 0.8207752468045225,
+      "eval_num_tokens": 2777465.0,
+      "eval_runtime": 162.1244,
+      "eval_samples_per_second": 9.53,
+      "eval_steps_per_second": 1.197,
+      "step": 1945
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3890,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.653233039031091e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-2334/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

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-2334/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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.00237968804112545,
+  "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": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-2334/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 %}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-2334/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
+}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-2334/trainer_state.json

@@ -0,0 +1,560 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 2334,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6110110306739807,
+      "epoch": 0.1287001287001287,
+      "grad_norm": 0.8611119389533997,
+      "learning_rate": 3.4130257962133866e-05,
+      "loss": 1.53956298828125,
+      "mean_token_accuracy": 0.6652342769503593,
+      "num_tokens": 73407.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.8662820833921433,
+      "epoch": 0.2574002574002574,
+      "grad_norm": 0.7405035495758057,
+      "learning_rate": 6.895705180104598e-05,
+      "loss": 0.7929539489746094,
+      "mean_token_accuracy": 0.7786347842216492,
+      "num_tokens": 143994.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7912819278240204,
+      "epoch": 0.3861003861003861,
+      "grad_norm": 0.6105485558509827,
+      "learning_rate": 0.00010378384563995809,
+      "loss": 0.7236511993408203,
+      "mean_token_accuracy": 0.7925467795133591,
+      "num_tokens": 216171.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.7777709531784057,
+      "epoch": 0.5148005148005148,
+      "grad_norm": 0.5781793594360352,
+      "learning_rate": 0.0001386106394788702,
+      "loss": 0.7024919891357422,
+      "mean_token_accuracy": 0.7969876372814179,
+      "num_tokens": 284702.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.7632609683275223,
+      "epoch": 0.6435006435006435,
+      "grad_norm": 0.6553444862365723,
+      "learning_rate": 0.00017343743331778232,
+      "loss": 0.7000718688964844,
+      "mean_token_accuracy": 0.7994742071628571,
+      "num_tokens": 356393.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.754165632724762,
+      "epoch": 0.7722007722007722,
+      "grad_norm": 0.634222149848938,
+      "learning_rate": 0.00020826422715669444,
+      "loss": 0.6909049987792969,
+      "mean_token_accuracy": 0.8016809666156769,
+      "num_tokens": 426916.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.7530711203813553,
+      "epoch": 0.9009009009009009,
+      "grad_norm": 0.7020156383514404,
+      "learning_rate": 0.00024309102099560653,
+      "loss": 0.69554931640625,
+      "mean_token_accuracy": 0.8002807641029358,
+      "num_tokens": 499603.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.5728044164242204,
+      "eval_loss": 0.6785851716995239,
+      "eval_mean_token_accuracy": 0.798433246993527,
+      "eval_num_tokens": 555493.0,
+      "eval_runtime": 162.4129,
+      "eval_samples_per_second": 9.513,
+      "eval_steps_per_second": 1.194,
+      "step": 389
+    },
+    {
+      "entropy": 0.7489313946829902,
+      "epoch": 1.0283140283140284,
+      "grad_norm": 0.7532815933227539,
+      "learning_rate": 0.0002709470016827303,
+      "loss": 0.6856581878662109,
+      "mean_token_accuracy": 0.8023027079273956,
+      "num_tokens": 570813.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.7238409864902496,
+      "epoch": 1.157014157014157,
+      "grad_norm": 1.2016215324401855,
+      "learning_rate": 0.0002707561443541359,
+      "loss": 0.6699818420410156,
+      "mean_token_accuracy": 0.8070302194356919,
+      "num_tokens": 642956.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.7388938587903976,
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.7279272079467773,
+      "learning_rate": 0.0002702930068622498,
+      "loss": 0.6728517150878907,
+      "mean_token_accuracy": 0.8049580943584442,
+      "num_tokens": 714498.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.7284485149383545,
+      "epoch": 1.4144144144144144,
+      "grad_norm": 0.8563987016677856,
+      "learning_rate": 0.0002695585213716931,
+      "loss": 0.6657986450195312,
+      "mean_token_accuracy": 0.8085588800907135,
+      "num_tokens": 785595.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.6960959500074386,
+      "epoch": 1.5431145431145432,
+      "grad_norm": 0.5145474672317505,
+      "learning_rate": 0.0002685541661937683,
+      "loss": 0.6358638763427734,
+      "mean_token_accuracy": 0.8131621342897415,
+      "num_tokens": 857551.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.7220414417982102,
+      "epoch": 1.6718146718146718,
+      "grad_norm": 0.9381059408187866,
+      "learning_rate": 0.00026728196281103746,
+      "loss": 0.6531407928466797,
+      "mean_token_accuracy": 0.811619822382927,
+      "num_tokens": 926864.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.6955459499359131,
+      "epoch": 1.8005148005148004,
+      "grad_norm": 0.6115108728408813,
+      "learning_rate": 0.0002657444718086503,
+      "loss": 0.6269588088989257,
+      "mean_token_accuracy": 0.8155373805761337,
+      "num_tokens": 998824.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.6929812705516816,
+      "epoch": 1.9292149292149292,
+      "grad_norm": 0.749489426612854,
+      "learning_rate": 0.0002639447877206115,
+      "loss": 0.629054069519043,
+      "mean_token_accuracy": 0.8183021235466004,
+      "num_tokens": 1069332.0,
+      "step": 750
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.5833694102223387,
+      "eval_loss": 0.6328718662261963,
+      "eval_mean_token_accuracy": 0.8159044071571114,
+      "eval_num_tokens": 1110986.0,
+      "eval_runtime": 161.885,
+      "eval_samples_per_second": 9.544,
+      "eval_steps_per_second": 1.198,
+      "step": 778
+    },
+    {
+      "entropy": 0.647241060480927,
+      "epoch": 2.056628056628057,
+      "grad_norm": 0.7070767879486084,
+      "learning_rate": 0.00026188653280135975,
+      "loss": 0.5823922348022461,
+      "mean_token_accuracy": 0.8265365301960647,
+      "num_tokens": 1141195.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5995378407835961,
+      "epoch": 2.1853281853281854,
+      "grad_norm": 0.8090486526489258,
+      "learning_rate": 0.0002595738497351955,
+      "loss": 0.5325597763061524,
+      "mean_token_accuracy": 0.8369336777925491,
+      "num_tokens": 1210708.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.6043145382404327,
+      "epoch": 2.314028314028314,
+      "grad_norm": 0.8279913067817688,
+      "learning_rate": 0.00025701139329823054,
+      "loss": 0.5414446258544922,
+      "mean_token_accuracy": 0.8361396533250809,
+      "num_tokens": 1283441.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.5953224584460258,
+      "epoch": 2.4427284427284426,
+      "grad_norm": 0.6075023412704468,
+      "learning_rate": 0.00025420432098964183,
+      "loss": 0.536654167175293,
+      "mean_token_accuracy": 0.8340093129873276,
+      "num_tokens": 1356418.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.5998479858040809,
+      "epoch": 2.571428571428571,
+      "grad_norm": 1.0311471223831177,
+      "learning_rate": 0.0002511582826510862,
+      "loss": 0.5372924423217773,
+      "mean_token_accuracy": 0.8366045409440994,
+      "num_tokens": 1427797.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.5980158120393753,
+      "epoch": 2.7001287001287,
+      "grad_norm": 0.5971426367759705,
+      "learning_rate": 0.0002478794090951689,
+      "loss": 0.5392885208129883,
+      "mean_token_accuracy": 0.8347727072238922,
+      "num_tokens": 1498082.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.5990680930018425,
+      "epoch": 2.828828828828829,
+      "grad_norm": 0.5662627220153809,
+      "learning_rate": 0.0002443742997658538,
+      "loss": 0.5360498428344727,
+      "mean_token_accuracy": 0.8371847170591354,
+      "num_tokens": 1568798.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.5957039377093315,
+      "epoch": 2.9575289575289574,
+      "grad_norm": 0.5043798685073853,
+      "learning_rate": 0.00024065000945565205,
+      "loss": 0.5342231369018555,
+      "mean_token_accuracy": 0.8380735236406326,
+      "num_tokens": 1643449.0,
+      "step": 1150
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.5346978819861854,
+      "eval_loss": 0.6255015134811401,
+      "eval_mean_token_accuracy": 0.8202014476368108,
+      "eval_num_tokens": 1666479.0,
+      "eval_runtime": 161.6098,
+      "eval_samples_per_second": 9.56,
+      "eval_steps_per_second": 1.2,
+      "step": 1167
+    },
+    {
+      "entropy": 0.5212209137401196,
+      "epoch": 3.0849420849420848,
+      "grad_norm": 0.7095440626144409,
+      "learning_rate": 0.00023671403410632178,
+      "loss": 0.45311901092529294,
+      "mean_token_accuracy": 0.856362871449403,
+      "num_tokens": 1713536.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.4701593083143234,
+      "epoch": 3.213642213642214,
+      "grad_norm": 0.6408083438873291,
+      "learning_rate": 0.0002325742957216607,
+      "loss": 0.39916397094726563,
+      "mean_token_accuracy": 0.8698061722517013,
+      "num_tokens": 1785609.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.4766591975092888,
+      "epoch": 3.3423423423423424,
+      "grad_norm": 0.6415093541145325,
+      "learning_rate": 0.0002282391264227552,
+      "loss": 0.4116698455810547,
+      "mean_token_accuracy": 0.8679435575008392,
+      "num_tokens": 1858651.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.4937947469949722,
+      "epoch": 3.471042471042471,
+      "grad_norm": 0.6549825072288513,
+      "learning_rate": 0.00022371725167778054,
+      "loss": 0.4296376037597656,
+      "mean_token_accuracy": 0.8609357953071595,
+      "num_tokens": 1928692.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.4920153194665909,
+      "epoch": 3.5997425997425996,
+      "grad_norm": 0.6452126502990723,
+      "learning_rate": 0.00021901777274010406,
+      "loss": 0.4307489013671875,
+      "mean_token_accuracy": 0.8606827831268311,
+      "num_tokens": 1998668.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.490042342543602,
+      "epoch": 3.7284427284427286,
+      "grad_norm": 0.5727734565734863,
+      "learning_rate": 0.0002141501483300395,
+      "loss": 0.4295254135131836,
+      "mean_token_accuracy": 0.8616545403003693,
+      "num_tokens": 2072809.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.49857193052768706,
+      "epoch": 3.857142857142857,
+      "grad_norm": 0.7732954025268555,
+      "learning_rate": 0.00020912417559712133,
+      "loss": 0.4289303207397461,
+      "mean_token_accuracy": 0.8616443765163422,
+      "num_tokens": 2142475.0,
+      "step": 1500
+    },
+    {
+      "entropy": 0.4746784272789955,
+      "epoch": 3.985842985842986,
+      "grad_norm": 0.5791187882423401,
+      "learning_rate": 0.00020394997040121726,
+      "loss": 0.4180263900756836,
+      "mean_token_accuracy": 0.866080379486084,
+      "num_tokens": 2214044.0,
+      "step": 1550
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.4793926059585257,
+      "eval_loss": 0.627627968788147,
+      "eval_mean_token_accuracy": 0.8233870095813397,
+      "eval_num_tokens": 2221972.0,
+      "eval_runtime": 162.0225,
+      "eval_samples_per_second": 9.536,
+      "eval_steps_per_second": 1.197,
+      "step": 1556
+    },
+    {
+      "entropy": 0.38195489000792454,
+      "epoch": 4.113256113256114,
+      "grad_norm": 0.6002617478370667,
+      "learning_rate": 0.0001986379469521669,
+      "loss": 0.30819049835205076,
+      "mean_token_accuracy": 0.8977848634575353,
+      "num_tokens": 2282164.0,
+      "step": 1600
+    },
+    {
+      "entropy": 0.3655787402391434,
+      "epoch": 4.241956241956242,
+      "grad_norm": 0.7100041508674622,
+      "learning_rate": 0.00019319879684892634,
+      "loss": 0.29959835052490236,
+      "mean_token_accuracy": 0.8991208010911942,
+      "num_tokens": 2353213.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.3821141055226326,
+      "epoch": 4.370656370656371,
+      "grad_norm": 0.5848307013511658,
+      "learning_rate": 0.00018764346756040715,
+      "loss": 0.313802490234375,
+      "mean_token_accuracy": 0.895167955160141,
+      "num_tokens": 2425068.0,
+      "step": 1700
+    },
+    {
+      "entropy": 0.37083797007799146,
+      "epoch": 4.499356499356499,
+      "grad_norm": 0.6447024941444397,
+      "learning_rate": 0.00018198314039132143,
+      "loss": 0.30583988189697264,
+      "mean_token_accuracy": 0.8961733293533325,
+      "num_tokens": 2498321.0,
+      "step": 1750
+    },
+    {
+      "entropy": 0.3791545969247818,
+      "epoch": 4.628056628056628,
+      "grad_norm": 0.6575382351875305,
+      "learning_rate": 0.00017622920797738184,
+      "loss": 0.3088031005859375,
+      "mean_token_accuracy": 0.8960050916671753,
+      "num_tokens": 2570321.0,
+      "step": 1800
+    },
+    {
+      "entropy": 0.3946831756830215,
+      "epoch": 4.756756756756757,
+      "grad_norm": 0.5351552963256836,
+      "learning_rate": 0.00017039325135515207,
+      "loss": 0.3229162979125977,
+      "mean_token_accuracy": 0.8920552498102188,
+      "num_tokens": 2642851.0,
+      "step": 1850
+    },
+    {
+      "entropy": 0.37298239797353744,
+      "epoch": 4.885456885456885,
+      "grad_norm": 0.7624587416648865,
+      "learning_rate": 0.00016448701665269964,
+      "loss": 0.3067934799194336,
+      "mean_token_accuracy": 0.8951873427629471,
+      "num_tokens": 2715629.0,
+      "step": 1900
+    },
+    {
+      "epoch": 5.0,
+      "eval_entropy": 0.3738150204887095,
+      "eval_loss": 0.7131896615028381,
+      "eval_mean_token_accuracy": 0.8207752468045225,
+      "eval_num_tokens": 2777465.0,
+      "eval_runtime": 162.1244,
+      "eval_samples_per_second": 9.53,
+      "eval_steps_per_second": 1.197,
+      "step": 1945
+    },
+    {
+      "entropy": 0.377820266617669,
+      "epoch": 5.012870012870013,
+      "grad_norm": 0.41990190744400024,
+      "learning_rate": 0.00015852239144796624,
+      "loss": 0.3058685111999512,
+      "mean_token_accuracy": 0.8964343480389527,
+      "num_tokens": 2784896.0,
+      "step": 1950
+    },
+    {
+      "entropy": 0.2714502356946468,
+      "epoch": 5.141570141570142,
+      "grad_norm": 0.422568678855896,
+      "learning_rate": 0.00015251138084243995,
+      "loss": 0.2093442153930664,
+      "mean_token_accuracy": 0.9311346983909607,
+      "num_tokens": 2854374.0,
+      "step": 2000
+    },
+    {
+      "entropy": 0.268475965410471,
+      "epoch": 5.27027027027027,
+      "grad_norm": 0.6637414693832397,
+      "learning_rate": 0.0001464660832982852,
+      "loss": 0.20736080169677734,
+      "mean_token_accuracy": 0.9289199805259705,
+      "num_tokens": 2927362.0,
+      "step": 2050
+    },
+    {
+      "entropy": 0.2644876340031624,
+      "epoch": 5.398970398970399,
+      "grad_norm": 0.47317707538604736,
+      "learning_rate": 0.00014039866628756467,
+      "loss": 0.20464908599853515,
+      "mean_token_accuracy": 0.9300856202840805,
+      "num_tokens": 3000143.0,
+      "step": 2100
+    },
+    {
+      "entropy": 0.2675253136456013,
+      "epoch": 5.527670527670527,
+      "grad_norm": 0.5253982543945312,
+      "learning_rate": 0.00013432134180256338,
+      "loss": 0.21154335021972656,
+      "mean_token_accuracy": 0.9283734840154648,
+      "num_tokens": 3072561.0,
+      "step": 2150
+    },
+    {
+      "entropy": 0.27213907435536383,
+      "epoch": 5.656370656370656,
+      "grad_norm": 0.46738553047180176,
+      "learning_rate": 0.00012824634177650664,
+      "loss": 0.21339216232299804,
+      "mean_token_accuracy": 0.9272083270549775,
+      "num_tokens": 3144831.0,
+      "step": 2200
+    },
+    {
+      "entropy": 0.2785488124191761,
+      "epoch": 5.785070785070785,
+      "grad_norm": 0.4469502866268158,
+      "learning_rate": 0.00012218589346414205,
+      "loss": 0.21601097106933595,
+      "mean_token_accuracy": 0.9255663657188415,
+      "num_tokens": 3215960.0,
+      "step": 2250
+    },
+    {
+      "entropy": 0.2699935150146484,
+      "epoch": 5.913770913770914,
+      "grad_norm": 0.7359778881072998,
+      "learning_rate": 0.00011615219483173828,
+      "loss": 0.20725584030151367,
+      "mean_token_accuracy": 0.9286630594730377,
+      "num_tokens": 3287499.0,
+      "step": 2300
+    },
+    {
+      "epoch": 6.0,
+      "eval_entropy": 0.26417383682174783,
+      "eval_loss": 0.8880229592323303,
+      "eval_mean_token_accuracy": 0.8159987201395723,
+      "eval_num_tokens": 3332958.0,
+      "eval_runtime": 162.0991,
+      "eval_samples_per_second": 9.531,
+      "eval_steps_per_second": 1.197,
+      "step": 2334
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3890,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.587061113467187e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-2723/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

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-2723/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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.00237968804112545,
+  "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": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-2723/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 %}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-2723/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
+}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-2723/trainer_state.json

@@ -0,0 +1,651 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 2723,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6110110306739807,
+      "epoch": 0.1287001287001287,
+      "grad_norm": 0.8611119389533997,
+      "learning_rate": 3.4130257962133866e-05,
+      "loss": 1.53956298828125,
+      "mean_token_accuracy": 0.6652342769503593,
+      "num_tokens": 73407.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.8662820833921433,
+      "epoch": 0.2574002574002574,
+      "grad_norm": 0.7405035495758057,
+      "learning_rate": 6.895705180104598e-05,
+      "loss": 0.7929539489746094,
+      "mean_token_accuracy": 0.7786347842216492,
+      "num_tokens": 143994.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7912819278240204,
+      "epoch": 0.3861003861003861,
+      "grad_norm": 0.6105485558509827,
+      "learning_rate": 0.00010378384563995809,
+      "loss": 0.7236511993408203,
+      "mean_token_accuracy": 0.7925467795133591,
+      "num_tokens": 216171.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.7777709531784057,
+      "epoch": 0.5148005148005148,
+      "grad_norm": 0.5781793594360352,
+      "learning_rate": 0.0001386106394788702,
+      "loss": 0.7024919891357422,
+      "mean_token_accuracy": 0.7969876372814179,
+      "num_tokens": 284702.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.7632609683275223,
+      "epoch": 0.6435006435006435,
+      "grad_norm": 0.6553444862365723,
+      "learning_rate": 0.00017343743331778232,
+      "loss": 0.7000718688964844,
+      "mean_token_accuracy": 0.7994742071628571,
+      "num_tokens": 356393.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.754165632724762,
+      "epoch": 0.7722007722007722,
+      "grad_norm": 0.634222149848938,
+      "learning_rate": 0.00020826422715669444,
+      "loss": 0.6909049987792969,
+      "mean_token_accuracy": 0.8016809666156769,
+      "num_tokens": 426916.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.7530711203813553,
+      "epoch": 0.9009009009009009,
+      "grad_norm": 0.7020156383514404,
+      "learning_rate": 0.00024309102099560653,
+      "loss": 0.69554931640625,
+      "mean_token_accuracy": 0.8002807641029358,
+      "num_tokens": 499603.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.5728044164242204,
+      "eval_loss": 0.6785851716995239,
+      "eval_mean_token_accuracy": 0.798433246993527,
+      "eval_num_tokens": 555493.0,
+      "eval_runtime": 162.4129,
+      "eval_samples_per_second": 9.513,
+      "eval_steps_per_second": 1.194,
+      "step": 389
+    },
+    {
+      "entropy": 0.7489313946829902,
+      "epoch": 1.0283140283140284,
+      "grad_norm": 0.7532815933227539,
+      "learning_rate": 0.0002709470016827303,
+      "loss": 0.6856581878662109,
+      "mean_token_accuracy": 0.8023027079273956,
+      "num_tokens": 570813.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.7238409864902496,
+      "epoch": 1.157014157014157,
+      "grad_norm": 1.2016215324401855,
+      "learning_rate": 0.0002707561443541359,
+      "loss": 0.6699818420410156,
+      "mean_token_accuracy": 0.8070302194356919,
+      "num_tokens": 642956.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.7388938587903976,
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.7279272079467773,
+      "learning_rate": 0.0002702930068622498,
+      "loss": 0.6728517150878907,
+      "mean_token_accuracy": 0.8049580943584442,
+      "num_tokens": 714498.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.7284485149383545,
+      "epoch": 1.4144144144144144,
+      "grad_norm": 0.8563987016677856,
+      "learning_rate": 0.0002695585213716931,
+      "loss": 0.6657986450195312,
+      "mean_token_accuracy": 0.8085588800907135,
+      "num_tokens": 785595.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.6960959500074386,
+      "epoch": 1.5431145431145432,
+      "grad_norm": 0.5145474672317505,
+      "learning_rate": 0.0002685541661937683,
+      "loss": 0.6358638763427734,
+      "mean_token_accuracy": 0.8131621342897415,
+      "num_tokens": 857551.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.7220414417982102,
+      "epoch": 1.6718146718146718,
+      "grad_norm": 0.9381059408187866,
+      "learning_rate": 0.00026728196281103746,
+      "loss": 0.6531407928466797,
+      "mean_token_accuracy": 0.811619822382927,
+      "num_tokens": 926864.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.6955459499359131,
+      "epoch": 1.8005148005148004,
+      "grad_norm": 0.6115108728408813,
+      "learning_rate": 0.0002657444718086503,
+      "loss": 0.6269588088989257,
+      "mean_token_accuracy": 0.8155373805761337,
+      "num_tokens": 998824.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.6929812705516816,
+      "epoch": 1.9292149292149292,
+      "grad_norm": 0.749489426612854,
+      "learning_rate": 0.0002639447877206115,
+      "loss": 0.629054069519043,
+      "mean_token_accuracy": 0.8183021235466004,
+      "num_tokens": 1069332.0,
+      "step": 750
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.5833694102223387,
+      "eval_loss": 0.6328718662261963,
+      "eval_mean_token_accuracy": 0.8159044071571114,
+      "eval_num_tokens": 1110986.0,
+      "eval_runtime": 161.885,
+      "eval_samples_per_second": 9.544,
+      "eval_steps_per_second": 1.198,
+      "step": 778
+    },
+    {
+      "entropy": 0.647241060480927,
+      "epoch": 2.056628056628057,
+      "grad_norm": 0.7070767879486084,
+      "learning_rate": 0.00026188653280135975,
+      "loss": 0.5823922348022461,
+      "mean_token_accuracy": 0.8265365301960647,
+      "num_tokens": 1141195.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5995378407835961,
+      "epoch": 2.1853281853281854,
+      "grad_norm": 0.8090486526489258,
+      "learning_rate": 0.0002595738497351955,
+      "loss": 0.5325597763061524,
+      "mean_token_accuracy": 0.8369336777925491,
+      "num_tokens": 1210708.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.6043145382404327,
+      "epoch": 2.314028314028314,
+      "grad_norm": 0.8279913067817688,
+      "learning_rate": 0.00025701139329823054,
+      "loss": 0.5414446258544922,
+      "mean_token_accuracy": 0.8361396533250809,
+      "num_tokens": 1283441.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.5953224584460258,
+      "epoch": 2.4427284427284426,
+      "grad_norm": 0.6075023412704468,
+      "learning_rate": 0.00025420432098964183,
+      "loss": 0.536654167175293,
+      "mean_token_accuracy": 0.8340093129873276,
+      "num_tokens": 1356418.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.5998479858040809,
+      "epoch": 2.571428571428571,
+      "grad_norm": 1.0311471223831177,
+      "learning_rate": 0.0002511582826510862,
+      "loss": 0.5372924423217773,
+      "mean_token_accuracy": 0.8366045409440994,
+      "num_tokens": 1427797.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.5980158120393753,
+      "epoch": 2.7001287001287,
+      "grad_norm": 0.5971426367759705,
+      "learning_rate": 0.0002478794090951689,
+      "loss": 0.5392885208129883,
+      "mean_token_accuracy": 0.8347727072238922,
+      "num_tokens": 1498082.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.5990680930018425,
+      "epoch": 2.828828828828829,
+      "grad_norm": 0.5662627220153809,
+      "learning_rate": 0.0002443742997658538,
+      "loss": 0.5360498428344727,
+      "mean_token_accuracy": 0.8371847170591354,
+      "num_tokens": 1568798.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.5957039377093315,
+      "epoch": 2.9575289575289574,
+      "grad_norm": 0.5043798685073853,
+      "learning_rate": 0.00024065000945565205,
+      "loss": 0.5342231369018555,
+      "mean_token_accuracy": 0.8380735236406326,
+      "num_tokens": 1643449.0,
+      "step": 1150
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.5346978819861854,
+      "eval_loss": 0.6255015134811401,
+      "eval_mean_token_accuracy": 0.8202014476368108,
+      "eval_num_tokens": 1666479.0,
+      "eval_runtime": 161.6098,
+      "eval_samples_per_second": 9.56,
+      "eval_steps_per_second": 1.2,
+      "step": 1167
+    },
+    {
+      "entropy": 0.5212209137401196,
+      "epoch": 3.0849420849420848,
+      "grad_norm": 0.7095440626144409,
+      "learning_rate": 0.00023671403410632178,
+      "loss": 0.45311901092529294,
+      "mean_token_accuracy": 0.856362871449403,
+      "num_tokens": 1713536.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.4701593083143234,
+      "epoch": 3.213642213642214,
+      "grad_norm": 0.6408083438873291,
+      "learning_rate": 0.0002325742957216607,
+      "loss": 0.39916397094726563,
+      "mean_token_accuracy": 0.8698061722517013,
+      "num_tokens": 1785609.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.4766591975092888,
+      "epoch": 3.3423423423423424,
+      "grad_norm": 0.6415093541145325,
+      "learning_rate": 0.0002282391264227552,
+      "loss": 0.4116698455810547,
+      "mean_token_accuracy": 0.8679435575008392,
+      "num_tokens": 1858651.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.4937947469949722,
+      "epoch": 3.471042471042471,
+      "grad_norm": 0.6549825072288513,
+      "learning_rate": 0.00022371725167778054,
+      "loss": 0.4296376037597656,
+      "mean_token_accuracy": 0.8609357953071595,
+      "num_tokens": 1928692.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.4920153194665909,
+      "epoch": 3.5997425997425996,
+      "grad_norm": 0.6452126502990723,
+      "learning_rate": 0.00021901777274010406,
+      "loss": 0.4307489013671875,
+      "mean_token_accuracy": 0.8606827831268311,
+      "num_tokens": 1998668.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.490042342543602,
+      "epoch": 3.7284427284427286,
+      "grad_norm": 0.5727734565734863,
+      "learning_rate": 0.0002141501483300395,
+      "loss": 0.4295254135131836,
+      "mean_token_accuracy": 0.8616545403003693,
+      "num_tokens": 2072809.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.49857193052768706,
+      "epoch": 3.857142857142857,
+      "grad_norm": 0.7732954025268555,
+      "learning_rate": 0.00020912417559712133,
+      "loss": 0.4289303207397461,
+      "mean_token_accuracy": 0.8616443765163422,
+      "num_tokens": 2142475.0,
+      "step": 1500
+    },
+    {
+      "entropy": 0.4746784272789955,
+      "epoch": 3.985842985842986,
+      "grad_norm": 0.5791187882423401,
+      "learning_rate": 0.00020394997040121726,
+      "loss": 0.4180263900756836,
+      "mean_token_accuracy": 0.866080379486084,
+      "num_tokens": 2214044.0,
+      "step": 1550
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.4793926059585257,
+      "eval_loss": 0.627627968788147,
+      "eval_mean_token_accuracy": 0.8233870095813397,
+      "eval_num_tokens": 2221972.0,
+      "eval_runtime": 162.0225,
+      "eval_samples_per_second": 9.536,
+      "eval_steps_per_second": 1.197,
+      "step": 1556
+    },
+    {
+      "entropy": 0.38195489000792454,
+      "epoch": 4.113256113256114,
+      "grad_norm": 0.6002617478370667,
+      "learning_rate": 0.0001986379469521669,
+      "loss": 0.30819049835205076,
+      "mean_token_accuracy": 0.8977848634575353,
+      "num_tokens": 2282164.0,
+      "step": 1600
+    },
+    {
+      "entropy": 0.3655787402391434,
+      "epoch": 4.241956241956242,
+      "grad_norm": 0.7100041508674622,
+      "learning_rate": 0.00019319879684892634,
+      "loss": 0.29959835052490236,
+      "mean_token_accuracy": 0.8991208010911942,
+      "num_tokens": 2353213.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.3821141055226326,
+      "epoch": 4.370656370656371,
+      "grad_norm": 0.5848307013511658,
+      "learning_rate": 0.00018764346756040715,
+      "loss": 0.313802490234375,
+      "mean_token_accuracy": 0.895167955160141,
+      "num_tokens": 2425068.0,
+      "step": 1700
+    },
+    {
+      "entropy": 0.37083797007799146,
+      "epoch": 4.499356499356499,
+      "grad_norm": 0.6447024941444397,
+      "learning_rate": 0.00018198314039132143,
+      "loss": 0.30583988189697264,
+      "mean_token_accuracy": 0.8961733293533325,
+      "num_tokens": 2498321.0,
+      "step": 1750
+    },
+    {
+      "entropy": 0.3791545969247818,
+      "epoch": 4.628056628056628,
+      "grad_norm": 0.6575382351875305,
+      "learning_rate": 0.00017622920797738184,
+      "loss": 0.3088031005859375,
+      "mean_token_accuracy": 0.8960050916671753,
+      "num_tokens": 2570321.0,
+      "step": 1800
+    },
+    {
+      "entropy": 0.3946831756830215,
+      "epoch": 4.756756756756757,
+      "grad_norm": 0.5351552963256836,
+      "learning_rate": 0.00017039325135515207,
+      "loss": 0.3229162979125977,
+      "mean_token_accuracy": 0.8920552498102188,
+      "num_tokens": 2642851.0,
+      "step": 1850
+    },
+    {
+      "entropy": 0.37298239797353744,
+      "epoch": 4.885456885456885,
+      "grad_norm": 0.7624587416648865,
+      "learning_rate": 0.00016448701665269964,
+      "loss": 0.3067934799194336,
+      "mean_token_accuracy": 0.8951873427629471,
+      "num_tokens": 2715629.0,
+      "step": 1900
+    },
+    {
+      "epoch": 5.0,
+      "eval_entropy": 0.3738150204887095,
+      "eval_loss": 0.7131896615028381,
+      "eval_mean_token_accuracy": 0.8207752468045225,
+      "eval_num_tokens": 2777465.0,
+      "eval_runtime": 162.1244,
+      "eval_samples_per_second": 9.53,
+      "eval_steps_per_second": 1.197,
+      "step": 1945
+    },
+    {
+      "entropy": 0.377820266617669,
+      "epoch": 5.012870012870013,
+      "grad_norm": 0.41990190744400024,
+      "learning_rate": 0.00015852239144796624,
+      "loss": 0.3058685111999512,
+      "mean_token_accuracy": 0.8964343480389527,
+      "num_tokens": 2784896.0,
+      "step": 1950
+    },
+    {
+      "entropy": 0.2714502356946468,
+      "epoch": 5.141570141570142,
+      "grad_norm": 0.422568678855896,
+      "learning_rate": 0.00015251138084243995,
+      "loss": 0.2093442153930664,
+      "mean_token_accuracy": 0.9311346983909607,
+      "num_tokens": 2854374.0,
+      "step": 2000
+    },
+    {
+      "entropy": 0.268475965410471,
+      "epoch": 5.27027027027027,
+      "grad_norm": 0.6637414693832397,
+      "learning_rate": 0.0001464660832982852,
+      "loss": 0.20736080169677734,
+      "mean_token_accuracy": 0.9289199805259705,
+      "num_tokens": 2927362.0,
+      "step": 2050
+    },
+    {
+      "entropy": 0.2644876340031624,
+      "epoch": 5.398970398970399,
+      "grad_norm": 0.47317707538604736,
+      "learning_rate": 0.00014039866628756467,
+      "loss": 0.20464908599853515,
+      "mean_token_accuracy": 0.9300856202840805,
+      "num_tokens": 3000143.0,
+      "step": 2100
+    },
+    {
+      "entropy": 0.2675253136456013,
+      "epoch": 5.527670527670527,
+      "grad_norm": 0.5253982543945312,
+      "learning_rate": 0.00013432134180256338,
+      "loss": 0.21154335021972656,
+      "mean_token_accuracy": 0.9283734840154648,
+      "num_tokens": 3072561.0,
+      "step": 2150
+    },
+    {
+      "entropy": 0.27213907435536383,
+      "epoch": 5.656370656370656,
+      "grad_norm": 0.46738553047180176,
+      "learning_rate": 0.00012824634177650664,
+      "loss": 0.21339216232299804,
+      "mean_token_accuracy": 0.9272083270549775,
+      "num_tokens": 3144831.0,
+      "step": 2200
+    },
+    {
+      "entropy": 0.2785488124191761,
+      "epoch": 5.785070785070785,
+      "grad_norm": 0.4469502866268158,
+      "learning_rate": 0.00012218589346414205,
+      "loss": 0.21601097106933595,
+      "mean_token_accuracy": 0.9255663657188415,
+      "num_tokens": 3215960.0,
+      "step": 2250
+    },
+    {
+      "entropy": 0.2699935150146484,
+      "epoch": 5.913770913770914,
+      "grad_norm": 0.7359778881072998,
+      "learning_rate": 0.00011615219483173828,
+      "loss": 0.20725584030151367,
+      "mean_token_accuracy": 0.9286630594730377,
+      "num_tokens": 3287499.0,
+      "step": 2300
+    },
+    {
+      "epoch": 6.0,
+      "eval_entropy": 0.26417383682174783,
+      "eval_loss": 0.8880229592323303,
+      "eval_mean_token_accuracy": 0.8159987201395723,
+      "eval_num_tokens": 3332958.0,
+      "eval_runtime": 162.0991,
+      "eval_samples_per_second": 9.531,
+      "eval_steps_per_second": 1.197,
+      "step": 2334
+    },
+    {
+      "entropy": 0.24814540704693458,
+      "epoch": 6.041184041184041,
+      "grad_norm": 0.4953760802745819,
+      "learning_rate": 0.00011015739000603316,
+      "loss": 0.18749794006347656,
+      "mean_token_accuracy": 0.9370789509831052,
+      "num_tokens": 3356879.0,
+      "step": 2350
+    },
+    {
+      "entropy": 0.19976271741092205,
+      "epoch": 6.1698841698841695,
+      "grad_norm": 0.4834803342819214,
+      "learning_rate": 0.00010421354483154553,
+      "loss": 0.14283526420593262,
+      "mean_token_accuracy": 0.9521516615152359,
+      "num_tokens": 3427587.0,
+      "step": 2400
+    },
+    {
+      "entropy": 0.2060488449037075,
+      "epoch": 6.298584298584299,
+      "grad_norm": 0.4888673722743988,
+      "learning_rate": 9.8332622585447e-05,
+      "loss": 0.14414511680603026,
+      "mean_token_accuracy": 0.9510996866226197,
+      "num_tokens": 3498688.0,
+      "step": 2450
+    },
+    {
+      "entropy": 0.2059111550450325,
+      "epoch": 6.427284427284428,
+      "grad_norm": 0.4064404368400574,
+      "learning_rate": 9.252645989887253e-05,
+      "loss": 0.14820143699645996,
+      "mean_token_accuracy": 0.9507584601640702,
+      "num_tokens": 3566137.0,
+      "step": 2500
+    },
+    {
+      "entropy": 0.19700154662132263,
+      "epoch": 6.555984555984556,
+      "grad_norm": 0.467965304851532,
+      "learning_rate": 8.680674293313417e-05,
+      "loss": 0.14303470611572267,
+      "mean_token_accuracy": 0.9515972435474396,
+      "num_tokens": 3639573.0,
+      "step": 2550
+    },
+    {
+      "entropy": 0.20180423602461814,
+      "epoch": 6.684684684684685,
+      "grad_norm": 0.36836138367652893,
+      "learning_rate": 8.118498385878736e-05,
+      "loss": 0.14280882835388184,
+      "mean_token_accuracy": 0.9515993863344192,
+      "num_tokens": 3710433.0,
+      "step": 2600
+    },
+    {
+      "entropy": 0.20024395987391472,
+      "epoch": 6.813384813384813,
+      "grad_norm": 0.38375866413116455,
+      "learning_rate": 7.567249768489171e-05,
+      "loss": 0.1427844524383545,
+      "mean_token_accuracy": 0.9524166631698608,
+      "num_tokens": 3781550.0,
+      "step": 2650
+    },
+    {
+      "entropy": 0.19561587080359458,
+      "epoch": 6.942084942084942,
+      "grad_norm": 0.41185441613197327,
+      "learning_rate": 7.028037948510187e-05,
+      "loss": 0.13993803024291993,
+      "mean_token_accuracy": 0.9522478264570237,
+      "num_tokens": 3854952.0,
+      "step": 2700
+    },
+    {
+      "epoch": 7.0,
+      "eval_entropy": 0.19501976062034823,
+      "eval_loss": 1.0653952360153198,
+      "eval_mean_token_accuracy": 0.8205490803595671,
+      "eval_num_tokens": 3888451.0,
+      "eval_runtime": 161.8533,
+      "eval_samples_per_second": 9.546,
+      "eval_steps_per_second": 1.199,
+      "step": 2723
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3890,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.516671077296845e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-3112/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

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-3112/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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.00237968804112545,
+  "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": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-3112/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 %}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-3112/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
+}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-3112/trainer_state.json

@@ -0,0 +1,742 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 3112,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6110110306739807,
+      "epoch": 0.1287001287001287,
+      "grad_norm": 0.8611119389533997,
+      "learning_rate": 3.4130257962133866e-05,
+      "loss": 1.53956298828125,
+      "mean_token_accuracy": 0.6652342769503593,
+      "num_tokens": 73407.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.8662820833921433,
+      "epoch": 0.2574002574002574,
+      "grad_norm": 0.7405035495758057,
+      "learning_rate": 6.895705180104598e-05,
+      "loss": 0.7929539489746094,
+      "mean_token_accuracy": 0.7786347842216492,
+      "num_tokens": 143994.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7912819278240204,
+      "epoch": 0.3861003861003861,
+      "grad_norm": 0.6105485558509827,
+      "learning_rate": 0.00010378384563995809,
+      "loss": 0.7236511993408203,
+      "mean_token_accuracy": 0.7925467795133591,
+      "num_tokens": 216171.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.7777709531784057,
+      "epoch": 0.5148005148005148,
+      "grad_norm": 0.5781793594360352,
+      "learning_rate": 0.0001386106394788702,
+      "loss": 0.7024919891357422,
+      "mean_token_accuracy": 0.7969876372814179,
+      "num_tokens": 284702.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.7632609683275223,
+      "epoch": 0.6435006435006435,
+      "grad_norm": 0.6553444862365723,
+      "learning_rate": 0.00017343743331778232,
+      "loss": 0.7000718688964844,
+      "mean_token_accuracy": 0.7994742071628571,
+      "num_tokens": 356393.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.754165632724762,
+      "epoch": 0.7722007722007722,
+      "grad_norm": 0.634222149848938,
+      "learning_rate": 0.00020826422715669444,
+      "loss": 0.6909049987792969,
+      "mean_token_accuracy": 0.8016809666156769,
+      "num_tokens": 426916.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.7530711203813553,
+      "epoch": 0.9009009009009009,
+      "grad_norm": 0.7020156383514404,
+      "learning_rate": 0.00024309102099560653,
+      "loss": 0.69554931640625,
+      "mean_token_accuracy": 0.8002807641029358,
+      "num_tokens": 499603.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.5728044164242204,
+      "eval_loss": 0.6785851716995239,
+      "eval_mean_token_accuracy": 0.798433246993527,
+      "eval_num_tokens": 555493.0,
+      "eval_runtime": 162.4129,
+      "eval_samples_per_second": 9.513,
+      "eval_steps_per_second": 1.194,
+      "step": 389
+    },
+    {
+      "entropy": 0.7489313946829902,
+      "epoch": 1.0283140283140284,
+      "grad_norm": 0.7532815933227539,
+      "learning_rate": 0.0002709470016827303,
+      "loss": 0.6856581878662109,
+      "mean_token_accuracy": 0.8023027079273956,
+      "num_tokens": 570813.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.7238409864902496,
+      "epoch": 1.157014157014157,
+      "grad_norm": 1.2016215324401855,
+      "learning_rate": 0.0002707561443541359,
+      "loss": 0.6699818420410156,
+      "mean_token_accuracy": 0.8070302194356919,
+      "num_tokens": 642956.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.7388938587903976,
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.7279272079467773,
+      "learning_rate": 0.0002702930068622498,
+      "loss": 0.6728517150878907,
+      "mean_token_accuracy": 0.8049580943584442,
+      "num_tokens": 714498.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.7284485149383545,
+      "epoch": 1.4144144144144144,
+      "grad_norm": 0.8563987016677856,
+      "learning_rate": 0.0002695585213716931,
+      "loss": 0.6657986450195312,
+      "mean_token_accuracy": 0.8085588800907135,
+      "num_tokens": 785595.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.6960959500074386,
+      "epoch": 1.5431145431145432,
+      "grad_norm": 0.5145474672317505,
+      "learning_rate": 0.0002685541661937683,
+      "loss": 0.6358638763427734,
+      "mean_token_accuracy": 0.8131621342897415,
+      "num_tokens": 857551.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.7220414417982102,
+      "epoch": 1.6718146718146718,
+      "grad_norm": 0.9381059408187866,
+      "learning_rate": 0.00026728196281103746,
+      "loss": 0.6531407928466797,
+      "mean_token_accuracy": 0.811619822382927,
+      "num_tokens": 926864.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.6955459499359131,
+      "epoch": 1.8005148005148004,
+      "grad_norm": 0.6115108728408813,
+      "learning_rate": 0.0002657444718086503,
+      "loss": 0.6269588088989257,
+      "mean_token_accuracy": 0.8155373805761337,
+      "num_tokens": 998824.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.6929812705516816,
+      "epoch": 1.9292149292149292,
+      "grad_norm": 0.749489426612854,
+      "learning_rate": 0.0002639447877206115,
+      "loss": 0.629054069519043,
+      "mean_token_accuracy": 0.8183021235466004,
+      "num_tokens": 1069332.0,
+      "step": 750
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.5833694102223387,
+      "eval_loss": 0.6328718662261963,
+      "eval_mean_token_accuracy": 0.8159044071571114,
+      "eval_num_tokens": 1110986.0,
+      "eval_runtime": 161.885,
+      "eval_samples_per_second": 9.544,
+      "eval_steps_per_second": 1.198,
+      "step": 778
+    },
+    {
+      "entropy": 0.647241060480927,
+      "epoch": 2.056628056628057,
+      "grad_norm": 0.7070767879486084,
+      "learning_rate": 0.00026188653280135975,
+      "loss": 0.5823922348022461,
+      "mean_token_accuracy": 0.8265365301960647,
+      "num_tokens": 1141195.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5995378407835961,
+      "epoch": 2.1853281853281854,
+      "grad_norm": 0.8090486526489258,
+      "learning_rate": 0.0002595738497351955,
+      "loss": 0.5325597763061524,
+      "mean_token_accuracy": 0.8369336777925491,
+      "num_tokens": 1210708.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.6043145382404327,
+      "epoch": 2.314028314028314,
+      "grad_norm": 0.8279913067817688,
+      "learning_rate": 0.00025701139329823054,
+      "loss": 0.5414446258544922,
+      "mean_token_accuracy": 0.8361396533250809,
+      "num_tokens": 1283441.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.5953224584460258,
+      "epoch": 2.4427284427284426,
+      "grad_norm": 0.6075023412704468,
+      "learning_rate": 0.00025420432098964183,
+      "loss": 0.536654167175293,
+      "mean_token_accuracy": 0.8340093129873276,
+      "num_tokens": 1356418.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.5998479858040809,
+      "epoch": 2.571428571428571,
+      "grad_norm": 1.0311471223831177,
+      "learning_rate": 0.0002511582826510862,
+      "loss": 0.5372924423217773,
+      "mean_token_accuracy": 0.8366045409440994,
+      "num_tokens": 1427797.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.5980158120393753,
+      "epoch": 2.7001287001287,
+      "grad_norm": 0.5971426367759705,
+      "learning_rate": 0.0002478794090951689,
+      "loss": 0.5392885208129883,
+      "mean_token_accuracy": 0.8347727072238922,
+      "num_tokens": 1498082.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.5990680930018425,
+      "epoch": 2.828828828828829,
+      "grad_norm": 0.5662627220153809,
+      "learning_rate": 0.0002443742997658538,
+      "loss": 0.5360498428344727,
+      "mean_token_accuracy": 0.8371847170591354,
+      "num_tokens": 1568798.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.5957039377093315,
+      "epoch": 2.9575289575289574,
+      "grad_norm": 0.5043798685073853,
+      "learning_rate": 0.00024065000945565205,
+      "loss": 0.5342231369018555,
+      "mean_token_accuracy": 0.8380735236406326,
+      "num_tokens": 1643449.0,
+      "step": 1150
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.5346978819861854,
+      "eval_loss": 0.6255015134811401,
+      "eval_mean_token_accuracy": 0.8202014476368108,
+      "eval_num_tokens": 1666479.0,
+      "eval_runtime": 161.6098,
+      "eval_samples_per_second": 9.56,
+      "eval_steps_per_second": 1.2,
+      "step": 1167
+    },
+    {
+      "entropy": 0.5212209137401196,
+      "epoch": 3.0849420849420848,
+      "grad_norm": 0.7095440626144409,
+      "learning_rate": 0.00023671403410632178,
+      "loss": 0.45311901092529294,
+      "mean_token_accuracy": 0.856362871449403,
+      "num_tokens": 1713536.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.4701593083143234,
+      "epoch": 3.213642213642214,
+      "grad_norm": 0.6408083438873291,
+      "learning_rate": 0.0002325742957216607,
+      "loss": 0.39916397094726563,
+      "mean_token_accuracy": 0.8698061722517013,
+      "num_tokens": 1785609.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.4766591975092888,
+      "epoch": 3.3423423423423424,
+      "grad_norm": 0.6415093541145325,
+      "learning_rate": 0.0002282391264227552,
+      "loss": 0.4116698455810547,
+      "mean_token_accuracy": 0.8679435575008392,
+      "num_tokens": 1858651.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.4937947469949722,
+      "epoch": 3.471042471042471,
+      "grad_norm": 0.6549825072288513,
+      "learning_rate": 0.00022371725167778054,
+      "loss": 0.4296376037597656,
+      "mean_token_accuracy": 0.8609357953071595,
+      "num_tokens": 1928692.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.4920153194665909,
+      "epoch": 3.5997425997425996,
+      "grad_norm": 0.6452126502990723,
+      "learning_rate": 0.00021901777274010406,
+      "loss": 0.4307489013671875,
+      "mean_token_accuracy": 0.8606827831268311,
+      "num_tokens": 1998668.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.490042342543602,
+      "epoch": 3.7284427284427286,
+      "grad_norm": 0.5727734565734863,
+      "learning_rate": 0.0002141501483300395,
+      "loss": 0.4295254135131836,
+      "mean_token_accuracy": 0.8616545403003693,
+      "num_tokens": 2072809.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.49857193052768706,
+      "epoch": 3.857142857142857,
+      "grad_norm": 0.7732954025268555,
+      "learning_rate": 0.00020912417559712133,
+      "loss": 0.4289303207397461,
+      "mean_token_accuracy": 0.8616443765163422,
+      "num_tokens": 2142475.0,
+      "step": 1500
+    },
+    {
+      "entropy": 0.4746784272789955,
+      "epoch": 3.985842985842986,
+      "grad_norm": 0.5791187882423401,
+      "learning_rate": 0.00020394997040121726,
+      "loss": 0.4180263900756836,
+      "mean_token_accuracy": 0.866080379486084,
+      "num_tokens": 2214044.0,
+      "step": 1550
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.4793926059585257,
+      "eval_loss": 0.627627968788147,
+      "eval_mean_token_accuracy": 0.8233870095813397,
+      "eval_num_tokens": 2221972.0,
+      "eval_runtime": 162.0225,
+      "eval_samples_per_second": 9.536,
+      "eval_steps_per_second": 1.197,
+      "step": 1556
+    },
+    {
+      "entropy": 0.38195489000792454,
+      "epoch": 4.113256113256114,
+      "grad_norm": 0.6002617478370667,
+      "learning_rate": 0.0001986379469521669,
+      "loss": 0.30819049835205076,
+      "mean_token_accuracy": 0.8977848634575353,
+      "num_tokens": 2282164.0,
+      "step": 1600
+    },
+    {
+      "entropy": 0.3655787402391434,
+      "epoch": 4.241956241956242,
+      "grad_norm": 0.7100041508674622,
+      "learning_rate": 0.00019319879684892634,
+      "loss": 0.29959835052490236,
+      "mean_token_accuracy": 0.8991208010911942,
+      "num_tokens": 2353213.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.3821141055226326,
+      "epoch": 4.370656370656371,
+      "grad_norm": 0.5848307013511658,
+      "learning_rate": 0.00018764346756040715,
+      "loss": 0.313802490234375,
+      "mean_token_accuracy": 0.895167955160141,
+      "num_tokens": 2425068.0,
+      "step": 1700
+    },
+    {
+      "entropy": 0.37083797007799146,
+      "epoch": 4.499356499356499,
+      "grad_norm": 0.6447024941444397,
+      "learning_rate": 0.00018198314039132143,
+      "loss": 0.30583988189697264,
+      "mean_token_accuracy": 0.8961733293533325,
+      "num_tokens": 2498321.0,
+      "step": 1750
+    },
+    {
+      "entropy": 0.3791545969247818,
+      "epoch": 4.628056628056628,
+      "grad_norm": 0.6575382351875305,
+      "learning_rate": 0.00017622920797738184,
+      "loss": 0.3088031005859375,
+      "mean_token_accuracy": 0.8960050916671753,
+      "num_tokens": 2570321.0,
+      "step": 1800
+    },
+    {
+      "entropy": 0.3946831756830215,
+      "epoch": 4.756756756756757,
+      "grad_norm": 0.5351552963256836,
+      "learning_rate": 0.00017039325135515207,
+      "loss": 0.3229162979125977,
+      "mean_token_accuracy": 0.8920552498102188,
+      "num_tokens": 2642851.0,
+      "step": 1850
+    },
+    {
+      "entropy": 0.37298239797353744,
+      "epoch": 4.885456885456885,
+      "grad_norm": 0.7624587416648865,
+      "learning_rate": 0.00016448701665269964,
+      "loss": 0.3067934799194336,
+      "mean_token_accuracy": 0.8951873427629471,
+      "num_tokens": 2715629.0,
+      "step": 1900
+    },
+    {
+      "epoch": 5.0,
+      "eval_entropy": 0.3738150204887095,
+      "eval_loss": 0.7131896615028381,
+      "eval_mean_token_accuracy": 0.8207752468045225,
+      "eval_num_tokens": 2777465.0,
+      "eval_runtime": 162.1244,
+      "eval_samples_per_second": 9.53,
+      "eval_steps_per_second": 1.197,
+      "step": 1945
+    },
+    {
+      "entropy": 0.377820266617669,
+      "epoch": 5.012870012870013,
+      "grad_norm": 0.41990190744400024,
+      "learning_rate": 0.00015852239144796624,
+      "loss": 0.3058685111999512,
+      "mean_token_accuracy": 0.8964343480389527,
+      "num_tokens": 2784896.0,
+      "step": 1950
+    },
+    {
+      "entropy": 0.2714502356946468,
+      "epoch": 5.141570141570142,
+      "grad_norm": 0.422568678855896,
+      "learning_rate": 0.00015251138084243995,
+      "loss": 0.2093442153930664,
+      "mean_token_accuracy": 0.9311346983909607,
+      "num_tokens": 2854374.0,
+      "step": 2000
+    },
+    {
+      "entropy": 0.268475965410471,
+      "epoch": 5.27027027027027,
+      "grad_norm": 0.6637414693832397,
+      "learning_rate": 0.0001464660832982852,
+      "loss": 0.20736080169677734,
+      "mean_token_accuracy": 0.9289199805259705,
+      "num_tokens": 2927362.0,
+      "step": 2050
+    },
+    {
+      "entropy": 0.2644876340031624,
+      "epoch": 5.398970398970399,
+      "grad_norm": 0.47317707538604736,
+      "learning_rate": 0.00014039866628756467,
+      "loss": 0.20464908599853515,
+      "mean_token_accuracy": 0.9300856202840805,
+      "num_tokens": 3000143.0,
+      "step": 2100
+    },
+    {
+      "entropy": 0.2675253136456013,
+      "epoch": 5.527670527670527,
+      "grad_norm": 0.5253982543945312,
+      "learning_rate": 0.00013432134180256338,
+      "loss": 0.21154335021972656,
+      "mean_token_accuracy": 0.9283734840154648,
+      "num_tokens": 3072561.0,
+      "step": 2150
+    },
+    {
+      "entropy": 0.27213907435536383,
+      "epoch": 5.656370656370656,
+      "grad_norm": 0.46738553047180176,
+      "learning_rate": 0.00012824634177650664,
+      "loss": 0.21339216232299804,
+      "mean_token_accuracy": 0.9272083270549775,
+      "num_tokens": 3144831.0,
+      "step": 2200
+    },
+    {
+      "entropy": 0.2785488124191761,
+      "epoch": 5.785070785070785,
+      "grad_norm": 0.4469502866268158,
+      "learning_rate": 0.00012218589346414205,
+      "loss": 0.21601097106933595,
+      "mean_token_accuracy": 0.9255663657188415,
+      "num_tokens": 3215960.0,
+      "step": 2250
+    },
+    {
+      "entropy": 0.2699935150146484,
+      "epoch": 5.913770913770914,
+      "grad_norm": 0.7359778881072998,
+      "learning_rate": 0.00011615219483173828,
+      "loss": 0.20725584030151367,
+      "mean_token_accuracy": 0.9286630594730377,
+      "num_tokens": 3287499.0,
+      "step": 2300
+    },
+    {
+      "epoch": 6.0,
+      "eval_entropy": 0.26417383682174783,
+      "eval_loss": 0.8880229592323303,
+      "eval_mean_token_accuracy": 0.8159987201395723,
+      "eval_num_tokens": 3332958.0,
+      "eval_runtime": 162.0991,
+      "eval_samples_per_second": 9.531,
+      "eval_steps_per_second": 1.197,
+      "step": 2334
+    },
+    {
+      "entropy": 0.24814540704693458,
+      "epoch": 6.041184041184041,
+      "grad_norm": 0.4953760802745819,
+      "learning_rate": 0.00011015739000603316,
+      "loss": 0.18749794006347656,
+      "mean_token_accuracy": 0.9370789509831052,
+      "num_tokens": 3356879.0,
+      "step": 2350
+    },
+    {
+      "entropy": 0.19976271741092205,
+      "epoch": 6.1698841698841695,
+      "grad_norm": 0.4834803342819214,
+      "learning_rate": 0.00010421354483154553,
+      "loss": 0.14283526420593262,
+      "mean_token_accuracy": 0.9521516615152359,
+      "num_tokens": 3427587.0,
+      "step": 2400
+    },
+    {
+      "entropy": 0.2060488449037075,
+      "epoch": 6.298584298584299,
+      "grad_norm": 0.4888673722743988,
+      "learning_rate": 9.8332622585447e-05,
+      "loss": 0.14414511680603026,
+      "mean_token_accuracy": 0.9510996866226197,
+      "num_tokens": 3498688.0,
+      "step": 2450
+    },
+    {
+      "entropy": 0.2059111550450325,
+      "epoch": 6.427284427284428,
+      "grad_norm": 0.4064404368400574,
+      "learning_rate": 9.252645989887253e-05,
+      "loss": 0.14820143699645996,
+      "mean_token_accuracy": 0.9507584601640702,
+      "num_tokens": 3566137.0,
+      "step": 2500
+    },
+    {
+      "entropy": 0.19700154662132263,
+      "epoch": 6.555984555984556,
+      "grad_norm": 0.467965304851532,
+      "learning_rate": 8.680674293313417e-05,
+      "loss": 0.14303470611572267,
+      "mean_token_accuracy": 0.9515972435474396,
+      "num_tokens": 3639573.0,
+      "step": 2550
+    },
+    {
+      "entropy": 0.20180423602461814,
+      "epoch": 6.684684684684685,
+      "grad_norm": 0.36836138367652893,
+      "learning_rate": 8.118498385878736e-05,
+      "loss": 0.14280882835388184,
+      "mean_token_accuracy": 0.9515993863344192,
+      "num_tokens": 3710433.0,
+      "step": 2600
+    },
+    {
+      "entropy": 0.20024395987391472,
+      "epoch": 6.813384813384813,
+      "grad_norm": 0.38375866413116455,
+      "learning_rate": 7.567249768489171e-05,
+      "loss": 0.1427844524383545,
+      "mean_token_accuracy": 0.9524166631698608,
+      "num_tokens": 3781550.0,
+      "step": 2650
+    },
+    {
+      "entropy": 0.19561587080359458,
+      "epoch": 6.942084942084942,
+      "grad_norm": 0.41185441613197327,
+      "learning_rate": 7.028037948510187e-05,
+      "loss": 0.13993803024291993,
+      "mean_token_accuracy": 0.9522478264570237,
+      "num_tokens": 3854952.0,
+      "step": 2700
+    },
+    {
+      "epoch": 7.0,
+      "eval_entropy": 0.19501976062034823,
+      "eval_loss": 1.0653952360153198,
+      "eval_mean_token_accuracy": 0.8205490803595671,
+      "eval_num_tokens": 3888451.0,
+      "eval_runtime": 161.8533,
+      "eval_samples_per_second": 9.546,
+      "eval_steps_per_second": 1.199,
+      "step": 2723
+    },
+    {
+      "entropy": 0.17789882526855277,
+      "epoch": 7.06949806949807,
+      "grad_norm": 0.41413992643356323,
+      "learning_rate": 6.50194820664261e-05,
+      "loss": 0.12078390121459961,
+      "mean_token_accuracy": 0.9589925727458916,
+      "num_tokens": 3928354.0,
+      "step": 2750
+    },
+    {
+      "entropy": 0.16781829454004765,
+      "epoch": 7.198198198198198,
+      "grad_norm": 0.25806066393852234,
+      "learning_rate": 5.990039412559906e-05,
+      "loss": 0.10963023185729981,
+      "mean_token_accuracy": 0.9617267113924026,
+      "num_tokens": 4000113.0,
+      "step": 2800
+    },
+    {
+      "entropy": 0.1649068508297205,
+      "epoch": 7.326898326898327,
+      "grad_norm": 0.27411890029907227,
+      "learning_rate": 5.493341893703393e-05,
+      "loss": 0.11152458190917969,
+      "mean_token_accuracy": 0.9620639663934708,
+      "num_tokens": 4071032.0,
+      "step": 2850
+    },
+    {
+      "entropy": 0.161333369910717,
+      "epoch": 7.455598455598455,
+      "grad_norm": 0.24944494664669037,
+      "learning_rate": 5.0128553615248396e-05,
+      "loss": 0.1094522476196289,
+      "mean_token_accuracy": 0.962428919672966,
+      "num_tokens": 4143616.0,
+      "step": 2900
+    },
+    {
+      "entropy": 0.15613057143986225,
+      "epoch": 7.584298584298584,
+      "grad_norm": 0.1455036848783493,
+      "learning_rate": 4.549546899350423e-05,
+      "loss": 0.11092090606689453,
+      "mean_token_accuracy": 0.9620462411642074,
+      "num_tokens": 4215664.0,
+      "step": 2950
+    },
+    {
+      "entropy": 0.1631234459578991,
+      "epoch": 7.712998712998713,
+      "grad_norm": 0.2129560261964798,
+      "learning_rate": 4.104349015915862e-05,
+      "loss": 0.1141857624053955,
+      "mean_token_accuracy": 0.9613765001296997,
+      "num_tokens": 4286387.0,
+      "step": 3000
+    },
+    {
+      "entropy": 0.1680422095954418,
+      "epoch": 7.841698841698841,
+      "grad_norm": 0.24886097013950348,
+      "learning_rate": 3.678157768490372e-05,
+      "loss": 0.11513191223144531,
+      "mean_token_accuracy": 0.9615794748067856,
+      "num_tokens": 4355875.0,
+      "step": 3050
+    },
+    {
+      "entropy": 0.16354035697877406,
+      "epoch": 7.97039897039897,
+      "grad_norm": 0.27600204944610596,
+      "learning_rate": 3.27183095936714e-05,
+      "loss": 0.1118631362915039,
+      "mean_token_accuracy": 0.9623224419355393,
+      "num_tokens": 4427088.0,
+      "step": 3100
+    },
+    {
+      "epoch": 8.0,
+      "eval_entropy": 0.16586771200305409,
+      "eval_loss": 1.204746961593628,
+      "eval_mean_token_accuracy": 0.8229975042883882,
+      "eval_num_tokens": 4443944.0,
+      "eval_runtime": 162.0251,
+      "eval_samples_per_second": 9.536,
+      "eval_steps_per_second": 1.197,
+      "step": 3112
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3890,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.445001770940518e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-3501/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

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-3501/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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.00237968804112545,
+  "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": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-3501/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 %}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-3501/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
+}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-3501/trainer_state.json

@@ -0,0 +1,833 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 3501,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6110110306739807,
+      "epoch": 0.1287001287001287,
+      "grad_norm": 0.8611119389533997,
+      "learning_rate": 3.4130257962133866e-05,
+      "loss": 1.53956298828125,
+      "mean_token_accuracy": 0.6652342769503593,
+      "num_tokens": 73407.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.8662820833921433,
+      "epoch": 0.2574002574002574,
+      "grad_norm": 0.7405035495758057,
+      "learning_rate": 6.895705180104598e-05,
+      "loss": 0.7929539489746094,
+      "mean_token_accuracy": 0.7786347842216492,
+      "num_tokens": 143994.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7912819278240204,
+      "epoch": 0.3861003861003861,
+      "grad_norm": 0.6105485558509827,
+      "learning_rate": 0.00010378384563995809,
+      "loss": 0.7236511993408203,
+      "mean_token_accuracy": 0.7925467795133591,
+      "num_tokens": 216171.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.7777709531784057,
+      "epoch": 0.5148005148005148,
+      "grad_norm": 0.5781793594360352,
+      "learning_rate": 0.0001386106394788702,
+      "loss": 0.7024919891357422,
+      "mean_token_accuracy": 0.7969876372814179,
+      "num_tokens": 284702.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.7632609683275223,
+      "epoch": 0.6435006435006435,
+      "grad_norm": 0.6553444862365723,
+      "learning_rate": 0.00017343743331778232,
+      "loss": 0.7000718688964844,
+      "mean_token_accuracy": 0.7994742071628571,
+      "num_tokens": 356393.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.754165632724762,
+      "epoch": 0.7722007722007722,
+      "grad_norm": 0.634222149848938,
+      "learning_rate": 0.00020826422715669444,
+      "loss": 0.6909049987792969,
+      "mean_token_accuracy": 0.8016809666156769,
+      "num_tokens": 426916.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.7530711203813553,
+      "epoch": 0.9009009009009009,
+      "grad_norm": 0.7020156383514404,
+      "learning_rate": 0.00024309102099560653,
+      "loss": 0.69554931640625,
+      "mean_token_accuracy": 0.8002807641029358,
+      "num_tokens": 499603.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.5728044164242204,
+      "eval_loss": 0.6785851716995239,
+      "eval_mean_token_accuracy": 0.798433246993527,
+      "eval_num_tokens": 555493.0,
+      "eval_runtime": 162.4129,
+      "eval_samples_per_second": 9.513,
+      "eval_steps_per_second": 1.194,
+      "step": 389
+    },
+    {
+      "entropy": 0.7489313946829902,
+      "epoch": 1.0283140283140284,
+      "grad_norm": 0.7532815933227539,
+      "learning_rate": 0.0002709470016827303,
+      "loss": 0.6856581878662109,
+      "mean_token_accuracy": 0.8023027079273956,
+      "num_tokens": 570813.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.7238409864902496,
+      "epoch": 1.157014157014157,
+      "grad_norm": 1.2016215324401855,
+      "learning_rate": 0.0002707561443541359,
+      "loss": 0.6699818420410156,
+      "mean_token_accuracy": 0.8070302194356919,
+      "num_tokens": 642956.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.7388938587903976,
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.7279272079467773,
+      "learning_rate": 0.0002702930068622498,
+      "loss": 0.6728517150878907,
+      "mean_token_accuracy": 0.8049580943584442,
+      "num_tokens": 714498.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.7284485149383545,
+      "epoch": 1.4144144144144144,
+      "grad_norm": 0.8563987016677856,
+      "learning_rate": 0.0002695585213716931,
+      "loss": 0.6657986450195312,
+      "mean_token_accuracy": 0.8085588800907135,
+      "num_tokens": 785595.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.6960959500074386,
+      "epoch": 1.5431145431145432,
+      "grad_norm": 0.5145474672317505,
+      "learning_rate": 0.0002685541661937683,
+      "loss": 0.6358638763427734,
+      "mean_token_accuracy": 0.8131621342897415,
+      "num_tokens": 857551.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.7220414417982102,
+      "epoch": 1.6718146718146718,
+      "grad_norm": 0.9381059408187866,
+      "learning_rate": 0.00026728196281103746,
+      "loss": 0.6531407928466797,
+      "mean_token_accuracy": 0.811619822382927,
+      "num_tokens": 926864.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.6955459499359131,
+      "epoch": 1.8005148005148004,
+      "grad_norm": 0.6115108728408813,
+      "learning_rate": 0.0002657444718086503,
+      "loss": 0.6269588088989257,
+      "mean_token_accuracy": 0.8155373805761337,
+      "num_tokens": 998824.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.6929812705516816,
+      "epoch": 1.9292149292149292,
+      "grad_norm": 0.749489426612854,
+      "learning_rate": 0.0002639447877206115,
+      "loss": 0.629054069519043,
+      "mean_token_accuracy": 0.8183021235466004,
+      "num_tokens": 1069332.0,
+      "step": 750
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.5833694102223387,
+      "eval_loss": 0.6328718662261963,
+      "eval_mean_token_accuracy": 0.8159044071571114,
+      "eval_num_tokens": 1110986.0,
+      "eval_runtime": 161.885,
+      "eval_samples_per_second": 9.544,
+      "eval_steps_per_second": 1.198,
+      "step": 778
+    },
+    {
+      "entropy": 0.647241060480927,
+      "epoch": 2.056628056628057,
+      "grad_norm": 0.7070767879486084,
+      "learning_rate": 0.00026188653280135975,
+      "loss": 0.5823922348022461,
+      "mean_token_accuracy": 0.8265365301960647,
+      "num_tokens": 1141195.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5995378407835961,
+      "epoch": 2.1853281853281854,
+      "grad_norm": 0.8090486526489258,
+      "learning_rate": 0.0002595738497351955,
+      "loss": 0.5325597763061524,
+      "mean_token_accuracy": 0.8369336777925491,
+      "num_tokens": 1210708.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.6043145382404327,
+      "epoch": 2.314028314028314,
+      "grad_norm": 0.8279913067817688,
+      "learning_rate": 0.00025701139329823054,
+      "loss": 0.5414446258544922,
+      "mean_token_accuracy": 0.8361396533250809,
+      "num_tokens": 1283441.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.5953224584460258,
+      "epoch": 2.4427284427284426,
+      "grad_norm": 0.6075023412704468,
+      "learning_rate": 0.00025420432098964183,
+      "loss": 0.536654167175293,
+      "mean_token_accuracy": 0.8340093129873276,
+      "num_tokens": 1356418.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.5998479858040809,
+      "epoch": 2.571428571428571,
+      "grad_norm": 1.0311471223831177,
+      "learning_rate": 0.0002511582826510862,
+      "loss": 0.5372924423217773,
+      "mean_token_accuracy": 0.8366045409440994,
+      "num_tokens": 1427797.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.5980158120393753,
+      "epoch": 2.7001287001287,
+      "grad_norm": 0.5971426367759705,
+      "learning_rate": 0.0002478794090951689,
+      "loss": 0.5392885208129883,
+      "mean_token_accuracy": 0.8347727072238922,
+      "num_tokens": 1498082.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.5990680930018425,
+      "epoch": 2.828828828828829,
+      "grad_norm": 0.5662627220153809,
+      "learning_rate": 0.0002443742997658538,
+      "loss": 0.5360498428344727,
+      "mean_token_accuracy": 0.8371847170591354,
+      "num_tokens": 1568798.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.5957039377093315,
+      "epoch": 2.9575289575289574,
+      "grad_norm": 0.5043798685073853,
+      "learning_rate": 0.00024065000945565205,
+      "loss": 0.5342231369018555,
+      "mean_token_accuracy": 0.8380735236406326,
+      "num_tokens": 1643449.0,
+      "step": 1150
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.5346978819861854,
+      "eval_loss": 0.6255015134811401,
+      "eval_mean_token_accuracy": 0.8202014476368108,
+      "eval_num_tokens": 1666479.0,
+      "eval_runtime": 161.6098,
+      "eval_samples_per_second": 9.56,
+      "eval_steps_per_second": 1.2,
+      "step": 1167
+    },
+    {
+      "entropy": 0.5212209137401196,
+      "epoch": 3.0849420849420848,
+      "grad_norm": 0.7095440626144409,
+      "learning_rate": 0.00023671403410632178,
+      "loss": 0.45311901092529294,
+      "mean_token_accuracy": 0.856362871449403,
+      "num_tokens": 1713536.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.4701593083143234,
+      "epoch": 3.213642213642214,
+      "grad_norm": 0.6408083438873291,
+      "learning_rate": 0.0002325742957216607,
+      "loss": 0.39916397094726563,
+      "mean_token_accuracy": 0.8698061722517013,
+      "num_tokens": 1785609.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.4766591975092888,
+      "epoch": 3.3423423423423424,
+      "grad_norm": 0.6415093541145325,
+      "learning_rate": 0.0002282391264227552,
+      "loss": 0.4116698455810547,
+      "mean_token_accuracy": 0.8679435575008392,
+      "num_tokens": 1858651.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.4937947469949722,
+      "epoch": 3.471042471042471,
+      "grad_norm": 0.6549825072288513,
+      "learning_rate": 0.00022371725167778054,
+      "loss": 0.4296376037597656,
+      "mean_token_accuracy": 0.8609357953071595,
+      "num_tokens": 1928692.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.4920153194665909,
+      "epoch": 3.5997425997425996,
+      "grad_norm": 0.6452126502990723,
+      "learning_rate": 0.00021901777274010406,
+      "loss": 0.4307489013671875,
+      "mean_token_accuracy": 0.8606827831268311,
+      "num_tokens": 1998668.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.490042342543602,
+      "epoch": 3.7284427284427286,
+      "grad_norm": 0.5727734565734863,
+      "learning_rate": 0.0002141501483300395,
+      "loss": 0.4295254135131836,
+      "mean_token_accuracy": 0.8616545403003693,
+      "num_tokens": 2072809.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.49857193052768706,
+      "epoch": 3.857142857142857,
+      "grad_norm": 0.7732954025268555,
+      "learning_rate": 0.00020912417559712133,
+      "loss": 0.4289303207397461,
+      "mean_token_accuracy": 0.8616443765163422,
+      "num_tokens": 2142475.0,
+      "step": 1500
+    },
+    {
+      "entropy": 0.4746784272789955,
+      "epoch": 3.985842985842986,
+      "grad_norm": 0.5791187882423401,
+      "learning_rate": 0.00020394997040121726,
+      "loss": 0.4180263900756836,
+      "mean_token_accuracy": 0.866080379486084,
+      "num_tokens": 2214044.0,
+      "step": 1550
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.4793926059585257,
+      "eval_loss": 0.627627968788147,
+      "eval_mean_token_accuracy": 0.8233870095813397,
+      "eval_num_tokens": 2221972.0,
+      "eval_runtime": 162.0225,
+      "eval_samples_per_second": 9.536,
+      "eval_steps_per_second": 1.197,
+      "step": 1556
+    },
+    {
+      "entropy": 0.38195489000792454,
+      "epoch": 4.113256113256114,
+      "grad_norm": 0.6002617478370667,
+      "learning_rate": 0.0001986379469521669,
+      "loss": 0.30819049835205076,
+      "mean_token_accuracy": 0.8977848634575353,
+      "num_tokens": 2282164.0,
+      "step": 1600
+    },
+    {
+      "entropy": 0.3655787402391434,
+      "epoch": 4.241956241956242,
+      "grad_norm": 0.7100041508674622,
+      "learning_rate": 0.00019319879684892634,
+      "loss": 0.29959835052490236,
+      "mean_token_accuracy": 0.8991208010911942,
+      "num_tokens": 2353213.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.3821141055226326,
+      "epoch": 4.370656370656371,
+      "grad_norm": 0.5848307013511658,
+      "learning_rate": 0.00018764346756040715,
+      "loss": 0.313802490234375,
+      "mean_token_accuracy": 0.895167955160141,
+      "num_tokens": 2425068.0,
+      "step": 1700
+    },
+    {
+      "entropy": 0.37083797007799146,
+      "epoch": 4.499356499356499,
+      "grad_norm": 0.6447024941444397,
+      "learning_rate": 0.00018198314039132143,
+      "loss": 0.30583988189697264,
+      "mean_token_accuracy": 0.8961733293533325,
+      "num_tokens": 2498321.0,
+      "step": 1750
+    },
+    {
+      "entropy": 0.3791545969247818,
+      "epoch": 4.628056628056628,
+      "grad_norm": 0.6575382351875305,
+      "learning_rate": 0.00017622920797738184,
+      "loss": 0.3088031005859375,
+      "mean_token_accuracy": 0.8960050916671753,
+      "num_tokens": 2570321.0,
+      "step": 1800
+    },
+    {
+      "entropy": 0.3946831756830215,
+      "epoch": 4.756756756756757,
+      "grad_norm": 0.5351552963256836,
+      "learning_rate": 0.00017039325135515207,
+      "loss": 0.3229162979125977,
+      "mean_token_accuracy": 0.8920552498102188,
+      "num_tokens": 2642851.0,
+      "step": 1850
+    },
+    {
+      "entropy": 0.37298239797353744,
+      "epoch": 4.885456885456885,
+      "grad_norm": 0.7624587416648865,
+      "learning_rate": 0.00016448701665269964,
+      "loss": 0.3067934799194336,
+      "mean_token_accuracy": 0.8951873427629471,
+      "num_tokens": 2715629.0,
+      "step": 1900
+    },
+    {
+      "epoch": 5.0,
+      "eval_entropy": 0.3738150204887095,
+      "eval_loss": 0.7131896615028381,
+      "eval_mean_token_accuracy": 0.8207752468045225,
+      "eval_num_tokens": 2777465.0,
+      "eval_runtime": 162.1244,
+      "eval_samples_per_second": 9.53,
+      "eval_steps_per_second": 1.197,
+      "step": 1945
+    },
+    {
+      "entropy": 0.377820266617669,
+      "epoch": 5.012870012870013,
+      "grad_norm": 0.41990190744400024,
+      "learning_rate": 0.00015852239144796624,
+      "loss": 0.3058685111999512,
+      "mean_token_accuracy": 0.8964343480389527,
+      "num_tokens": 2784896.0,
+      "step": 1950
+    },
+    {
+      "entropy": 0.2714502356946468,
+      "epoch": 5.141570141570142,
+      "grad_norm": 0.422568678855896,
+      "learning_rate": 0.00015251138084243995,
+      "loss": 0.2093442153930664,
+      "mean_token_accuracy": 0.9311346983909607,
+      "num_tokens": 2854374.0,
+      "step": 2000
+    },
+    {
+      "entropy": 0.268475965410471,
+      "epoch": 5.27027027027027,
+      "grad_norm": 0.6637414693832397,
+      "learning_rate": 0.0001464660832982852,
+      "loss": 0.20736080169677734,
+      "mean_token_accuracy": 0.9289199805259705,
+      "num_tokens": 2927362.0,
+      "step": 2050
+    },
+    {
+      "entropy": 0.2644876340031624,
+      "epoch": 5.398970398970399,
+      "grad_norm": 0.47317707538604736,
+      "learning_rate": 0.00014039866628756467,
+      "loss": 0.20464908599853515,
+      "mean_token_accuracy": 0.9300856202840805,
+      "num_tokens": 3000143.0,
+      "step": 2100
+    },
+    {
+      "entropy": 0.2675253136456013,
+      "epoch": 5.527670527670527,
+      "grad_norm": 0.5253982543945312,
+      "learning_rate": 0.00013432134180256338,
+      "loss": 0.21154335021972656,
+      "mean_token_accuracy": 0.9283734840154648,
+      "num_tokens": 3072561.0,
+      "step": 2150
+    },
+    {
+      "entropy": 0.27213907435536383,
+      "epoch": 5.656370656370656,
+      "grad_norm": 0.46738553047180176,
+      "learning_rate": 0.00012824634177650664,
+      "loss": 0.21339216232299804,
+      "mean_token_accuracy": 0.9272083270549775,
+      "num_tokens": 3144831.0,
+      "step": 2200
+    },
+    {
+      "entropy": 0.2785488124191761,
+      "epoch": 5.785070785070785,
+      "grad_norm": 0.4469502866268158,
+      "learning_rate": 0.00012218589346414205,
+      "loss": 0.21601097106933595,
+      "mean_token_accuracy": 0.9255663657188415,
+      "num_tokens": 3215960.0,
+      "step": 2250
+    },
+    {
+      "entropy": 0.2699935150146484,
+      "epoch": 5.913770913770914,
+      "grad_norm": 0.7359778881072998,
+      "learning_rate": 0.00011615219483173828,
+      "loss": 0.20725584030151367,
+      "mean_token_accuracy": 0.9286630594730377,
+      "num_tokens": 3287499.0,
+      "step": 2300
+    },
+    {
+      "epoch": 6.0,
+      "eval_entropy": 0.26417383682174783,
+      "eval_loss": 0.8880229592323303,
+      "eval_mean_token_accuracy": 0.8159987201395723,
+      "eval_num_tokens": 3332958.0,
+      "eval_runtime": 162.0991,
+      "eval_samples_per_second": 9.531,
+      "eval_steps_per_second": 1.197,
+      "step": 2334
+    },
+    {
+      "entropy": 0.24814540704693458,
+      "epoch": 6.041184041184041,
+      "grad_norm": 0.4953760802745819,
+      "learning_rate": 0.00011015739000603316,
+      "loss": 0.18749794006347656,
+      "mean_token_accuracy": 0.9370789509831052,
+      "num_tokens": 3356879.0,
+      "step": 2350
+    },
+    {
+      "entropy": 0.19976271741092205,
+      "epoch": 6.1698841698841695,
+      "grad_norm": 0.4834803342819214,
+      "learning_rate": 0.00010421354483154553,
+      "loss": 0.14283526420593262,
+      "mean_token_accuracy": 0.9521516615152359,
+      "num_tokens": 3427587.0,
+      "step": 2400
+    },
+    {
+      "entropy": 0.2060488449037075,
+      "epoch": 6.298584298584299,
+      "grad_norm": 0.4888673722743988,
+      "learning_rate": 9.8332622585447e-05,
+      "loss": 0.14414511680603026,
+      "mean_token_accuracy": 0.9510996866226197,
+      "num_tokens": 3498688.0,
+      "step": 2450
+    },
+    {
+      "entropy": 0.2059111550450325,
+      "epoch": 6.427284427284428,
+      "grad_norm": 0.4064404368400574,
+      "learning_rate": 9.252645989887253e-05,
+      "loss": 0.14820143699645996,
+      "mean_token_accuracy": 0.9507584601640702,
+      "num_tokens": 3566137.0,
+      "step": 2500
+    },
+    {
+      "entropy": 0.19700154662132263,
+      "epoch": 6.555984555984556,
+      "grad_norm": 0.467965304851532,
+      "learning_rate": 8.680674293313417e-05,
+      "loss": 0.14303470611572267,
+      "mean_token_accuracy": 0.9515972435474396,
+      "num_tokens": 3639573.0,
+      "step": 2550
+    },
+    {
+      "entropy": 0.20180423602461814,
+      "epoch": 6.684684684684685,
+      "grad_norm": 0.36836138367652893,
+      "learning_rate": 8.118498385878736e-05,
+      "loss": 0.14280882835388184,
+      "mean_token_accuracy": 0.9515993863344192,
+      "num_tokens": 3710433.0,
+      "step": 2600
+    },
+    {
+      "entropy": 0.20024395987391472,
+      "epoch": 6.813384813384813,
+      "grad_norm": 0.38375866413116455,
+      "learning_rate": 7.567249768489171e-05,
+      "loss": 0.1427844524383545,
+      "mean_token_accuracy": 0.9524166631698608,
+      "num_tokens": 3781550.0,
+      "step": 2650
+    },
+    {
+      "entropy": 0.19561587080359458,
+      "epoch": 6.942084942084942,
+      "grad_norm": 0.41185441613197327,
+      "learning_rate": 7.028037948510187e-05,
+      "loss": 0.13993803024291993,
+      "mean_token_accuracy": 0.9522478264570237,
+      "num_tokens": 3854952.0,
+      "step": 2700
+    },
+    {
+      "epoch": 7.0,
+      "eval_entropy": 0.19501976062034823,
+      "eval_loss": 1.0653952360153198,
+      "eval_mean_token_accuracy": 0.8205490803595671,
+      "eval_num_tokens": 3888451.0,
+      "eval_runtime": 161.8533,
+      "eval_samples_per_second": 9.546,
+      "eval_steps_per_second": 1.199,
+      "step": 2723
+    },
+    {
+      "entropy": 0.17789882526855277,
+      "epoch": 7.06949806949807,
+      "grad_norm": 0.41413992643356323,
+      "learning_rate": 6.50194820664261e-05,
+      "loss": 0.12078390121459961,
+      "mean_token_accuracy": 0.9589925727458916,
+      "num_tokens": 3928354.0,
+      "step": 2750
+    },
+    {
+      "entropy": 0.16781829454004765,
+      "epoch": 7.198198198198198,
+      "grad_norm": 0.25806066393852234,
+      "learning_rate": 5.990039412559906e-05,
+      "loss": 0.10963023185729981,
+      "mean_token_accuracy": 0.9617267113924026,
+      "num_tokens": 4000113.0,
+      "step": 2800
+    },
+    {
+      "entropy": 0.1649068508297205,
+      "epoch": 7.326898326898327,
+      "grad_norm": 0.27411890029907227,
+      "learning_rate": 5.493341893703393e-05,
+      "loss": 0.11152458190917969,
+      "mean_token_accuracy": 0.9620639663934708,
+      "num_tokens": 4071032.0,
+      "step": 2850
+    },
+    {
+      "entropy": 0.161333369910717,
+      "epoch": 7.455598455598455,
+      "grad_norm": 0.24944494664669037,
+      "learning_rate": 5.0128553615248396e-05,
+      "loss": 0.1094522476196289,
+      "mean_token_accuracy": 0.962428919672966,
+      "num_tokens": 4143616.0,
+      "step": 2900
+    },
+    {
+      "entropy": 0.15613057143986225,
+      "epoch": 7.584298584298584,
+      "grad_norm": 0.1455036848783493,
+      "learning_rate": 4.549546899350423e-05,
+      "loss": 0.11092090606689453,
+      "mean_token_accuracy": 0.9620462411642074,
+      "num_tokens": 4215664.0,
+      "step": 2950
+    },
+    {
+      "entropy": 0.1631234459578991,
+      "epoch": 7.712998712998713,
+      "grad_norm": 0.2129560261964798,
+      "learning_rate": 4.104349015915862e-05,
+      "loss": 0.1141857624053955,
+      "mean_token_accuracy": 0.9613765001296997,
+      "num_tokens": 4286387.0,
+      "step": 3000
+    },
+    {
+      "entropy": 0.1680422095954418,
+      "epoch": 7.841698841698841,
+      "grad_norm": 0.24886097013950348,
+      "learning_rate": 3.678157768490372e-05,
+      "loss": 0.11513191223144531,
+      "mean_token_accuracy": 0.9615794748067856,
+      "num_tokens": 4355875.0,
+      "step": 3050
+    },
+    {
+      "entropy": 0.16354035697877406,
+      "epoch": 7.97039897039897,
+      "grad_norm": 0.27600204944610596,
+      "learning_rate": 3.27183095936714e-05,
+      "loss": 0.1118631362915039,
+      "mean_token_accuracy": 0.9623224419355393,
+      "num_tokens": 4427088.0,
+      "step": 3100
+    },
+    {
+      "epoch": 8.0,
+      "eval_entropy": 0.16586771200305409,
+      "eval_loss": 1.204746961593628,
+      "eval_mean_token_accuracy": 0.8229975042883882,
+      "eval_num_tokens": 4443944.0,
+      "eval_runtime": 162.0251,
+      "eval_samples_per_second": 9.536,
+      "eval_steps_per_second": 1.197,
+      "step": 3112
+    },
+    {
+      "entropy": 0.1515902608934075,
+      "epoch": 8.097812097812097,
+      "grad_norm": 0.14122211933135986,
+      "learning_rate": 2.88618640935022e-05,
+      "loss": 0.09900871276855469,
+      "mean_token_accuracy": 0.9665110737386376,
+      "num_tokens": 4497867.0,
+      "step": 3150
+    },
+    {
+      "entropy": 0.14593622356653213,
+      "epoch": 8.226512226512227,
+      "grad_norm": 0.20527532696723938,
+      "learning_rate": 2.5220003117128462e-05,
+      "loss": 0.09842084884643555,
+      "mean_token_accuracy": 0.9655911487340927,
+      "num_tokens": 4568534.0,
+      "step": 3200
+    },
+    {
+      "entropy": 0.1482392605394125,
+      "epoch": 8.355212355212355,
+      "grad_norm": 0.13207173347473145,
+      "learning_rate": 2.1800056699401584e-05,
+      "loss": 0.09551989555358886,
+      "mean_token_accuracy": 0.9650829958915711,
+      "num_tokens": 4642530.0,
+      "step": 3250
+    },
+    {
+      "entropy": 0.15284131653606892,
+      "epoch": 8.483912483912484,
+      "grad_norm": 0.1777282953262329,
+      "learning_rate": 1.860890822400777e-05,
+      "loss": 0.10169261932373047,
+      "mean_token_accuracy": 0.9635212075710297,
+      "num_tokens": 4711573.0,
+      "step": 3300
+    },
+    {
+      "entropy": 0.15095721945166587,
+      "epoch": 8.612612612612612,
+      "grad_norm": 0.14988408982753754,
+      "learning_rate": 1.5652980569165692e-05,
+      "loss": 0.10045011520385742,
+      "mean_token_accuracy": 0.96439110994339,
+      "num_tokens": 4782666.0,
+      "step": 3350
+    },
+    {
+      "entropy": 0.15411154814064504,
+      "epoch": 8.741312741312742,
+      "grad_norm": 0.14055995643138885,
+      "learning_rate": 1.2938223180191691e-05,
+      "loss": 0.1034860897064209,
+      "mean_token_accuracy": 0.963447842001915,
+      "num_tokens": 4852180.0,
+      "step": 3400
+    },
+    {
+      "entropy": 0.14739766091108322,
+      "epoch": 8.87001287001287,
+      "grad_norm": 0.15041407942771912,
+      "learning_rate": 1.0470100094950792e-05,
+      "loss": 0.09690508842468262,
+      "mean_token_accuracy": 0.96561603307724,
+      "num_tokens": 4926402.0,
+      "step": 3450
+    },
+    {
+      "entropy": 0.1498453303426504,
+      "epoch": 8.998712998712998,
+      "grad_norm": 0.1293368935585022,
+      "learning_rate": 8.253578946296125e-06,
+      "loss": 0.09874271392822266,
+      "mean_token_accuracy": 0.9647125631570816,
+      "num_tokens": 4998841.0,
+      "step": 3500
+    },
+    {
+      "epoch": 9.0,
+      "eval_entropy": 0.151532097729211,
+      "eval_loss": 1.302620768547058,
+      "eval_mean_token_accuracy": 0.8230925079473516,
+      "eval_num_tokens": 4999437.0,
+      "eval_runtime": 161.5816,
+      "eval_samples_per_second": 9.562,
+      "eval_steps_per_second": 1.201,
+      "step": 3501
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3890,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.377780321673011e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-389/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

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-389/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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.00237968804112545,
+  "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": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-389/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 %}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-389/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
+}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-389/trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 389,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6110110306739807,
+      "epoch": 0.1287001287001287,
+      "grad_norm": 0.8611119389533997,
+      "learning_rate": 3.4130257962133866e-05,
+      "loss": 1.53956298828125,
+      "mean_token_accuracy": 0.6652342769503593,
+      "num_tokens": 73407.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.8662820833921433,
+      "epoch": 0.2574002574002574,
+      "grad_norm": 0.7405035495758057,
+      "learning_rate": 6.895705180104598e-05,
+      "loss": 0.7929539489746094,
+      "mean_token_accuracy": 0.7786347842216492,
+      "num_tokens": 143994.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7912819278240204,
+      "epoch": 0.3861003861003861,
+      "grad_norm": 0.6105485558509827,
+      "learning_rate": 0.00010378384563995809,
+      "loss": 0.7236511993408203,
+      "mean_token_accuracy": 0.7925467795133591,
+      "num_tokens": 216171.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.7777709531784057,
+      "epoch": 0.5148005148005148,
+      "grad_norm": 0.5781793594360352,
+      "learning_rate": 0.0001386106394788702,
+      "loss": 0.7024919891357422,
+      "mean_token_accuracy": 0.7969876372814179,
+      "num_tokens": 284702.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.7632609683275223,
+      "epoch": 0.6435006435006435,
+      "grad_norm": 0.6553444862365723,
+      "learning_rate": 0.00017343743331778232,
+      "loss": 0.7000718688964844,
+      "mean_token_accuracy": 0.7994742071628571,
+      "num_tokens": 356393.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.754165632724762,
+      "epoch": 0.7722007722007722,
+      "grad_norm": 0.634222149848938,
+      "learning_rate": 0.00020826422715669444,
+      "loss": 0.6909049987792969,
+      "mean_token_accuracy": 0.8016809666156769,
+      "num_tokens": 426916.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.7530711203813553,
+      "epoch": 0.9009009009009009,
+      "grad_norm": 0.7020156383514404,
+      "learning_rate": 0.00024309102099560653,
+      "loss": 0.69554931640625,
+      "mean_token_accuracy": 0.8002807641029358,
+      "num_tokens": 499603.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.5728044164242204,
+      "eval_loss": 0.6785851716995239,
+      "eval_mean_token_accuracy": 0.798433246993527,
+      "eval_num_tokens": 555493.0,
+      "eval_runtime": 162.4129,
+      "eval_samples_per_second": 9.513,
+      "eval_steps_per_second": 1.194,
+      "step": 389
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3890,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.306612280369152e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-3890/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

productivity_original_Estonian/Qwen3-14B-Base_productivity_splits_original_features_train_productivity_splits_original_features_test2/checkpoint-3890/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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.00237968804112545,
+  "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": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

random_original_Estonian/Qwen3-14B-Base_random_splits_original_features_train_random_splits_original_features_test1/checkpoint-1224/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

random_original_Estonian/Qwen3-14B-Base_random_splits_original_features_train_random_splits_original_features_test1/checkpoint-1224/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B-Base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.09831666542701797,
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

random_original_Estonian/Qwen3-14B-Base_random_splits_original_features_train_random_splits_original_features_test1/checkpoint-1224/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 %}

random_original_Estonian/Qwen3-14B-Base_random_splits_original_features_train_random_splits_original_features_test1/checkpoint-1224/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
+}

random_original_Estonian/Qwen3-14B-Base_random_splits_original_features_train_random_splits_original_features_test1/checkpoint-1224/trainer_state.json

@@ -0,0 +1,307 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1224,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6558652856945992,
+      "epoch": 0.12277470841006753,
+      "grad_norm": 0.8294193148612976,
+      "learning_rate": 2.604481765338724e-05,
+      "loss": 1.5730807495117187,
+      "mean_token_accuracy": 0.6558220008015633,
+      "num_tokens": 137019.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.8554385647177696,
+      "epoch": 0.24554941682013506,
+      "grad_norm": 1.029894232749939,
+      "learning_rate": 5.2621162197659935e-05,
+      "loss": 0.7961322021484375,
+      "mean_token_accuracy": 0.7755533090233803,
+      "num_tokens": 267448.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7380270153284073,
+      "epoch": 0.3683241252302026,
+      "grad_norm": 0.6096898913383484,
+      "learning_rate": 7.919750674193263e-05,
+      "loss": 0.6843100738525391,
+      "mean_token_accuracy": 0.7998733684420586,
+      "num_tokens": 409071.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.6932123881578446,
+      "epoch": 0.4910988336402701,
+      "grad_norm": 0.5934288501739502,
+      "learning_rate": 0.00010577385128620532,
+      "loss": 0.6458084106445312,
+      "mean_token_accuracy": 0.8083393195271492,
+      "num_tokens": 542207.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.6840551143884659,
+      "epoch": 0.6138735420503376,
+      "grad_norm": 0.4665544331073761,
+      "learning_rate": 0.00013235019583047802,
+      "loss": 0.6333241653442383,
+      "mean_token_accuracy": 0.8122684139013291,
+      "num_tokens": 679619.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.6649293206632138,
+      "epoch": 0.7366482504604052,
+      "grad_norm": 0.47893014550209045,
+      "learning_rate": 0.00015892654037475069,
+      "loss": 0.6107040786743164,
+      "mean_token_accuracy": 0.8165940269827843,
+      "num_tokens": 815397.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.6492742404341698,
+      "epoch": 0.8594229588704727,
+      "grad_norm": 0.6059293746948242,
+      "learning_rate": 0.0001855028849190234,
+      "loss": 0.597186050415039,
+      "mean_token_accuracy": 0.8217281407117843,
+      "num_tokens": 949315.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.642182088047266,
+      "epoch": 0.9821976672805403,
+      "grad_norm": 0.3793066143989563,
+      "learning_rate": 0.0002120792294632961,
+      "loss": 0.5949800491333008,
+      "mean_token_accuracy": 0.8229166463017463,
+      "num_tokens": 1082903.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.6541631272860936,
+      "eval_loss": 0.5903413891792297,
+      "eval_mean_token_accuracy": 0.8252546640804835,
+      "eval_num_tokens": 1101768.0,
+      "eval_runtime": 108.9056,
+      "eval_samples_per_second": 12.818,
+      "eval_steps_per_second": 1.607,
+      "step": 408
+    },
+    {
+      "entropy": 0.6077755300829253,
+      "epoch": 1.1031307550644567,
+      "grad_norm": 0.5028847455978394,
+      "learning_rate": 0.00021679626884558217,
+      "loss": 0.5617346954345703,
+      "mean_token_accuracy": 0.8301527442665875,
+      "num_tokens": 1223073.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.5860125370323658,
+      "epoch": 1.2259054634745243,
+      "grad_norm": 0.38494572043418884,
+      "learning_rate": 0.00021653451093163906,
+      "loss": 0.5437137985229492,
+      "mean_token_accuracy": 0.8346565261483192,
+      "num_tokens": 1360978.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.5945393888652325,
+      "epoch": 1.3486801718845918,
+      "grad_norm": 0.5123576521873474,
+      "learning_rate": 0.00021607496224450087,
+      "loss": 0.54191650390625,
+      "mean_token_accuracy": 0.8335164493322372,
+      "num_tokens": 1492506.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.6083934807777405,
+      "epoch": 1.4714548802946594,
+      "grad_norm": 0.46661439538002014,
+      "learning_rate": 0.000215418463597734,
+      "loss": 0.5550478744506836,
+      "mean_token_accuracy": 0.8311341696977615,
+      "num_tokens": 1622275.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.5862340961396694,
+      "epoch": 1.5942295887047269,
+      "grad_norm": 0.49572765827178955,
+      "learning_rate": 0.00021456621615453177,
+      "loss": 0.5297146606445312,
+      "mean_token_accuracy": 0.8360210624337197,
+      "num_tokens": 1756450.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.5832360745966434,
+      "epoch": 1.7170042971147943,
+      "grad_norm": 0.35520103573799133,
+      "learning_rate": 0.0002135197792300053,
+      "loss": 0.5287040328979492,
+      "mean_token_accuracy": 0.8368027776479721,
+      "num_tokens": 1890634.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.5792283065617084,
+      "epoch": 1.839779005524862,
+      "grad_norm": 0.3548352122306824,
+      "learning_rate": 0.00021228106743818178,
+      "loss": 0.5251237487792969,
+      "mean_token_accuracy": 0.8396679371595382,
+      "num_tokens": 2028046.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.5694268302619457,
+      "epoch": 1.9625537139349294,
+      "grad_norm": 0.3476282060146332,
+      "learning_rate": 0.00021085234718892933,
+      "loss": 0.5189918899536132,
+      "mean_token_accuracy": 0.8398650133609772,
+      "num_tokens": 2163703.0,
+      "step": 800
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.5552395452771868,
+      "eval_loss": 0.5418588519096375,
+      "eval_mean_token_accuracy": 0.8379638079234532,
+      "eval_num_tokens": 2203536.0,
+      "eval_runtime": 108.6649,
+      "eval_samples_per_second": 12.847,
+      "eval_steps_per_second": 1.61,
+      "step": 816
+    },
+    {
+      "entropy": 0.5162206395023365,
+      "epoch": 2.0834868017188457,
+      "grad_norm": 0.3772931396961212,
+      "learning_rate": 0.0002092362325412188,
+      "loss": 0.4619992446899414,
+      "mean_token_accuracy": 0.8528054483650904,
+      "num_tokens": 2298231.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.5109021583199501,
+      "epoch": 2.2062615101289134,
+      "grad_norm": 0.4661090672016144,
+      "learning_rate": 0.000207435680420309,
+      "loss": 0.4571444702148437,
+      "mean_token_accuracy": 0.8552933797240257,
+      "num_tokens": 2427608.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.5012516237795352,
+      "epoch": 2.329036218538981,
+      "grad_norm": 0.5193169713020325,
+      "learning_rate": 0.0002054539852076065,
+      "loss": 0.45432735443115235,
+      "mean_token_accuracy": 0.8564087572693825,
+      "num_tokens": 2565982.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.5173932652175427,
+      "epoch": 2.4518109269490487,
+      "grad_norm": 0.4666334390640259,
+      "learning_rate": 0.00020329477271309812,
+      "loss": 0.4616986083984375,
+      "mean_token_accuracy": 0.8532203987240792,
+      "num_tokens": 2695545.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.5169526914507151,
+      "epoch": 2.574585635359116,
+      "grad_norm": 0.47921115159988403,
+      "learning_rate": 0.0002009619935413857,
+      "loss": 0.45737281799316404,
+      "mean_token_accuracy": 0.8535552659630775,
+      "num_tokens": 2829781.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.50618562489748,
+      "epoch": 2.6973603437691835,
+      "grad_norm": 0.3407684862613678,
+      "learning_rate": 0.00019845991586345935,
+      "loss": 0.45972068786621095,
+      "mean_token_accuracy": 0.8532172521948814,
+      "num_tokens": 2970162.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.5158357314765454,
+      "epoch": 2.820135052179251,
+      "grad_norm": 0.47901391983032227,
+      "learning_rate": 0.00019579311760743563,
+      "loss": 0.46119583129882813,
+      "mean_token_accuracy": 0.8536588314175606,
+      "num_tokens": 3103775.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.5069115920364857,
+      "epoch": 2.942909760589319,
+      "grad_norm": 0.4287651479244232,
+      "learning_rate": 0.00019296647808254838,
+      "loss": 0.45447597503662107,
+      "mean_token_accuracy": 0.856622197329998,
+      "num_tokens": 3241634.0,
+      "step": 1200
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.5097703012398311,
+      "eval_loss": 0.5291272401809692,
+      "eval_mean_token_accuracy": 0.8438761404582432,
+      "eval_num_tokens": 3305304.0,
+      "eval_runtime": 108.6946,
+      "eval_samples_per_second": 12.843,
+      "eval_steps_per_second": 1.61,
+      "step": 1224
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4080,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.376308378051789e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

random_original_Estonian/Qwen3-14B-Base_random_splits_original_features_train_random_splits_original_features_test1/checkpoint-1632/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