experiments

checkpoint-100000/README.md

@@ -0,0 +1,209 @@
+---
+base_model: slovak-nlp/mistral-sk-7b
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:slovak-nlp/mistral-sk-7b
+- llama-factory
+- lora
+- transformers
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-100000/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "MistralForCausalLM",
+    "parent_library": "transformers.models.mistral.modeling_mistral",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "slovak-nlp/mistral-sk-7b",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-100000/chat_template.jinja

@@ -0,0 +1,9 @@
+{% set system_message = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.
+
+' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '### Instruction:
+' + content + '
+
+### Response:
+' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '
+
+' }}{% endif %}{% endfor %}

checkpoint-100000/tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

hruska_10_experiments_results/hruska_10_experiments_results/01_baseline_r16_a16_lr5e5_adamw/01_baseline_r16_a16_lr5e5_adamw.yaml

@@ -0,0 +1,65 @@
+stage: sft
+do_train: true
+do_eval: true
+
+model_name_or_path: slovak-nlp/mistral-sk-7b
+trust_remote_code: true
+
+dataset_dir: data
+dataset: aya_slovak_100k_fixed
+template: alpaca
+cutoff_len: 1024
+packing: false
+train_on_prompt: false
+
+finetuning_type: lora
+lora_rank: 16
+lora_alpha: 16
+lora_dropout: 0.0
+lora_target: q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj
+
+per_device_train_batch_size: 1
+per_device_eval_batch_size: 1
+gradient_accumulation_steps: 8
+
+learning_rate: 0.00005
+lr_scheduler_type: cosine
+warmup_steps: 500
+max_grad_norm: 0.5
+
+bf16: true
+fp16: false
+optim: adamw_torch
+flash_attn: auto
+plot_loss: true
+
+ddp_timeout: 180000000
+ddp_find_unused_parameters: false
+include_num_input_tokens_seen: true
+enable_thinking: false
+
+use_unsloth: true
+use_unsloth_gc: true
+
+streaming: false
+
+max_steps: 6250
+
+eval_strategy: steps
+val_size: 1000
+eval_steps: 1250
+
+overwrite_cache: false
+overwrite_output_dir: true
+output_dir: /home/schwarc/diplomovka/hruska_compare9_100k_fixed_01_baseline_r16_a16_lr5e5_adamw
+
+logging_steps: 50
+save_steps: 6250
+save_total_limit: 1
+report_to: none
+
+seed: 42
+
+accelerator_config:
+  dispatch_batches: false
+  split_batches: false

hruska_10_experiments_results/hruska_10_experiments_results/02_optimizer_adamw8bit_r16_a16_lr5e5/02_optimizer_adamw8bit_r16_a16_lr5e5.yaml

@@ -0,0 +1,65 @@
+stage: sft
+do_train: true
+do_eval: true
+
+model_name_or_path: slovak-nlp/mistral-sk-7b
+trust_remote_code: true
+
+dataset_dir: data
+dataset: aya_slovak_100k_fixed
+template: alpaca
+cutoff_len: 1024
+packing: false
+train_on_prompt: false
+
+finetuning_type: lora
+lora_rank: 16
+lora_alpha: 16
+lora_dropout: 0.0
+lora_target: q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj
+
+per_device_train_batch_size: 1
+per_device_eval_batch_size: 1
+gradient_accumulation_steps: 8
+
+learning_rate: 0.00005
+lr_scheduler_type: cosine
+warmup_steps: 500
+max_grad_norm: 0.5
+
+bf16: true
+fp16: false
+optim: adamw_8bit
+flash_attn: auto
+plot_loss: true
+
+ddp_timeout: 180000000
+ddp_find_unused_parameters: false
+include_num_input_tokens_seen: true
+enable_thinking: false
+
+use_unsloth: true
+use_unsloth_gc: true
+
+streaming: false
+
+max_steps: 6250
+
+eval_strategy: steps
+val_size: 1000
+eval_steps: 1250
+
+overwrite_cache: false
+overwrite_output_dir: true
+output_dir: /home/schwarc/diplomovka/hruska_compare9_100k_fixed_02_optimizer_adamw8bit_r16_a16_lr5e5
+
+logging_steps: 50
+save_steps: 6250
+save_total_limit: 1
+report_to: none
+
+seed: 42
+
+accelerator_config:
+  dispatch_batches: false
+  split_batches: false

hruska_10_experiments_results/hruska_10_experiments_results/03_rank8_a16_lr5e5/03_rank8_a16_lr5e5.yaml

@@ -0,0 +1,65 @@
+stage: sft
+do_train: true
+do_eval: true
+
+model_name_or_path: slovak-nlp/mistral-sk-7b
+trust_remote_code: true
+
+dataset_dir: data
+dataset: aya_slovak_100k_fixed
+template: alpaca
+cutoff_len: 1024
+packing: false
+train_on_prompt: false
+
+finetuning_type: lora
+lora_rank: 8
+lora_alpha: 16
+lora_dropout: 0.0
+lora_target: q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj
+
+per_device_train_batch_size: 1
+per_device_eval_batch_size: 1
+gradient_accumulation_steps: 8
+
+learning_rate: 0.00005
+lr_scheduler_type: cosine
+warmup_steps: 500
+max_grad_norm: 0.5
+
+bf16: true
+fp16: false
+optim: adamw_torch
+flash_attn: auto
+plot_loss: true
+
+ddp_timeout: 180000000
+ddp_find_unused_parameters: false
+include_num_input_tokens_seen: true
+enable_thinking: false
+
+use_unsloth: true
+use_unsloth_gc: true
+
+streaming: false
+
+max_steps: 6250
+
+eval_strategy: steps
+val_size: 1000
+eval_steps: 1250
+
+overwrite_cache: false
+overwrite_output_dir: true
+output_dir: /home/schwarc/diplomovka/hruska_compare9_100k_fixed_03_rank8_a16_lr5e5
+
+logging_steps: 50
+save_steps: 6250
+save_total_limit: 1
+report_to: none
+
+seed: 42
+
+accelerator_config:
+  dispatch_batches: false
+  split_batches: false

hruska_10_experiments_results/hruska_10_experiments_results/04_rank32_a32_lr5e5/04_rank32_a32_lr5e5.yaml

@@ -0,0 +1,65 @@
+stage: sft
+do_train: true
+do_eval: true
+
+model_name_or_path: slovak-nlp/mistral-sk-7b
+trust_remote_code: true
+
+dataset_dir: data
+dataset: aya_slovak_100k_fixed
+template: alpaca
+cutoff_len: 1024
+packing: false
+train_on_prompt: false
+
+finetuning_type: lora
+lora_rank: 32
+lora_alpha: 32
+lora_dropout: 0.0
+lora_target: q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj
+
+per_device_train_batch_size: 1
+per_device_eval_batch_size: 1
+gradient_accumulation_steps: 8
+
+learning_rate: 0.00005
+lr_scheduler_type: cosine
+warmup_steps: 500
+max_grad_norm: 0.5
+
+bf16: true
+fp16: false
+optim: adamw_torch
+flash_attn: auto
+plot_loss: true
+
+ddp_timeout: 180000000
+ddp_find_unused_parameters: false
+include_num_input_tokens_seen: true
+enable_thinking: false
+
+use_unsloth: true
+use_unsloth_gc: true
+
+streaming: false
+
+max_steps: 6250
+
+eval_strategy: steps
+val_size: 1000
+eval_steps: 1250
+
+overwrite_cache: false
+overwrite_output_dir: true
+output_dir: /home/schwarc/diplomovka/hruska_compare9_100k_fixed_04_rank32_a32_lr5e5
+
+logging_steps: 50
+save_steps: 6250
+save_total_limit: 1
+report_to: none
+
+seed: 42
+
+accelerator_config:
+  dispatch_batches: false
+  split_batches: false

hruska_10_experiments_results/hruska_10_experiments_results/05_r16_alpha32_lr5e5/05_r16_alpha32_lr5e5.yaml

@@ -0,0 +1,65 @@
+stage: sft
+do_train: true
+do_eval: true
+
+model_name_or_path: slovak-nlp/mistral-sk-7b
+trust_remote_code: true
+
+dataset_dir: data
+dataset: aya_slovak_100k_fixed
+template: alpaca
+cutoff_len: 1024
+packing: false
+train_on_prompt: false
+
+finetuning_type: lora
+lora_rank: 16
+lora_alpha: 32
+lora_dropout: 0.0
+lora_target: q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj
+
+per_device_train_batch_size: 1
+per_device_eval_batch_size: 1
+gradient_accumulation_steps: 8
+
+learning_rate: 0.00005
+lr_scheduler_type: cosine
+warmup_steps: 500
+max_grad_norm: 0.5
+
+bf16: true
+fp16: false
+optim: adamw_torch
+flash_attn: auto
+plot_loss: true
+
+ddp_timeout: 180000000
+ddp_find_unused_parameters: false
+include_num_input_tokens_seen: true
+enable_thinking: false
+
+use_unsloth: true
+use_unsloth_gc: true
+
+streaming: false
+
+max_steps: 6250
+
+eval_strategy: steps
+val_size: 1000
+eval_steps: 1250
+
+overwrite_cache: false
+overwrite_output_dir: true
+output_dir: /home/schwarc/diplomovka/hruska_compare9_100k_fixed_05_r16_alpha32_lr5e5
+
+logging_steps: 50
+save_steps: 6250
+save_total_limit: 1
+report_to: none
+
+seed: 42
+
+accelerator_config:
+  dispatch_batches: false
+  split_batches: false

hruska_10_experiments_results/hruska_10_experiments_results/06_lr1e4_r16_a16/06_lr1e4_r16_a16.yaml

@@ -0,0 +1,65 @@
+stage: sft
+do_train: true
+do_eval: true
+
+model_name_or_path: slovak-nlp/mistral-sk-7b
+trust_remote_code: true
+
+dataset_dir: data
+dataset: aya_slovak_100k_fixed
+template: alpaca
+cutoff_len: 1024
+packing: false
+train_on_prompt: false
+
+finetuning_type: lora
+lora_rank: 16
+lora_alpha: 16
+lora_dropout: 0.0
+lora_target: q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj
+
+per_device_train_batch_size: 1
+per_device_eval_batch_size: 1
+gradient_accumulation_steps: 8
+
+learning_rate: 0.0001
+lr_scheduler_type: cosine
+warmup_steps: 500
+max_grad_norm: 0.5
+
+bf16: true
+fp16: false
+optim: adamw_torch
+flash_attn: auto
+plot_loss: true
+
+ddp_timeout: 180000000
+ddp_find_unused_parameters: false
+include_num_input_tokens_seen: true
+enable_thinking: false
+
+use_unsloth: true
+use_unsloth_gc: true
+
+streaming: false
+
+max_steps: 6250
+
+eval_strategy: steps
+val_size: 1000
+eval_steps: 1250
+
+overwrite_cache: false
+overwrite_output_dir: true
+output_dir: /home/schwarc/diplomovka/hruska_compare9_100k_fixed_06_lr1e4_r16_a16
+
+logging_steps: 50
+save_steps: 6250
+save_total_limit: 1
+report_to: none
+
+seed: 42
+
+accelerator_config:
+  dispatch_batches: false
+  split_batches: false

hruska_10_experiments_results/hruska_10_experiments_results/07_lr2e5_r16_a16/07_lr2e5_r16_a16.yaml

@@ -0,0 +1,65 @@
+stage: sft
+do_train: true
+do_eval: true
+
+model_name_or_path: slovak-nlp/mistral-sk-7b
+trust_remote_code: true
+
+dataset_dir: data
+dataset: aya_slovak_100k_fixed
+template: alpaca
+cutoff_len: 1024
+packing: false
+train_on_prompt: false
+
+finetuning_type: lora
+lora_rank: 16
+lora_alpha: 16
+lora_dropout: 0.0
+lora_target: q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj
+
+per_device_train_batch_size: 1
+per_device_eval_batch_size: 1
+gradient_accumulation_steps: 8
+
+learning_rate: 0.00002
+lr_scheduler_type: cosine
+warmup_steps: 500
+max_grad_norm: 0.5
+
+bf16: true
+fp16: false
+optim: adamw_torch
+flash_attn: auto
+plot_loss: true
+
+ddp_timeout: 180000000
+ddp_find_unused_parameters: false
+include_num_input_tokens_seen: true
+enable_thinking: false
+
+use_unsloth: true
+use_unsloth_gc: true
+
+streaming: false
+
+max_steps: 6250
+
+eval_strategy: steps
+val_size: 1000
+eval_steps: 1250
+
+overwrite_cache: false
+overwrite_output_dir: true
+output_dir: /home/schwarc/diplomovka/hruska_compare9_100k_fixed_07_lr2e5_r16_a16
+
+logging_steps: 50
+save_steps: 6250
+save_total_limit: 1
+report_to: none
+
+seed: 42
+
+accelerator_config:
+  dispatch_batches: false
+  split_batches: false

hruska_10_experiments_results/hruska_10_experiments_results/08_attention_only_r16_a16_lr5e5/08_attention_only_r16_a16_lr5e5.yaml

@@ -0,0 +1,65 @@
+stage: sft
+do_train: true
+do_eval: true
+
+model_name_or_path: slovak-nlp/mistral-sk-7b
+trust_remote_code: true
+
+dataset_dir: data
+dataset: aya_slovak_100k_fixed
+template: alpaca
+cutoff_len: 1024
+packing: false
+train_on_prompt: false
+
+finetuning_type: lora
+lora_rank: 16
+lora_alpha: 16
+lora_dropout: 0.0
+lora_target: q_proj,k_proj,v_proj,o_proj
+
+per_device_train_batch_size: 1
+per_device_eval_batch_size: 1
+gradient_accumulation_steps: 8
+
+learning_rate: 0.00005
+lr_scheduler_type: cosine
+warmup_steps: 500
+max_grad_norm: 0.5
+
+bf16: true
+fp16: false
+optim: adamw_torch
+flash_attn: auto
+plot_loss: true
+
+ddp_timeout: 180000000
+ddp_find_unused_parameters: false
+include_num_input_tokens_seen: true
+enable_thinking: false
+
+use_unsloth: true
+use_unsloth_gc: true
+
+streaming: false
+
+max_steps: 6250
+
+eval_strategy: steps
+val_size: 1000
+eval_steps: 1250
+
+overwrite_cache: false
+overwrite_output_dir: true
+output_dir: /home/schwarc/diplomovka/hruska_compare9_100k_fixed_08_attention_only_r16_a16_lr5e5
+
+logging_steps: 50
+save_steps: 6250
+save_total_limit: 1
+report_to: none
+
+seed: 42
+
+accelerator_config:
+  dispatch_batches: false
+  split_batches: false

hruska_10_experiments_results/hruska_10_experiments_results/09_batch2_accum4_r16_a16_lr5e5/09_batch2_accum4_r16_a16_lr5e5.yaml

@@ -0,0 +1,65 @@
+stage: sft
+do_train: true
+do_eval: true
+
+model_name_or_path: slovak-nlp/mistral-sk-7b
+trust_remote_code: true
+
+dataset_dir: data
+dataset: aya_slovak_100k_fixed
+template: alpaca
+cutoff_len: 1024
+packing: false
+train_on_prompt: false
+
+finetuning_type: lora
+lora_rank: 16
+lora_alpha: 16
+lora_dropout: 0.0
+lora_target: q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj
+
+per_device_train_batch_size: 2
+per_device_eval_batch_size: 1
+gradient_accumulation_steps: 4
+
+learning_rate: 0.00005
+lr_scheduler_type: cosine
+warmup_steps: 500
+max_grad_norm: 0.5
+
+bf16: true
+fp16: false
+optim: adamw_torch
+flash_attn: auto
+plot_loss: true
+
+ddp_timeout: 180000000
+ddp_find_unused_parameters: false
+include_num_input_tokens_seen: true
+enable_thinking: false
+
+use_unsloth: true
+use_unsloth_gc: true
+
+streaming: false
+
+max_steps: 6250
+
+eval_strategy: steps
+val_size: 1000
+eval_steps: 1250
+
+overwrite_cache: false
+overwrite_output_dir: true
+output_dir: /home/schwarc/diplomovka/hruska_compare9_100k_fixed_09_batch2_accum4_r16_a16_lr5e5
+
+logging_steps: 50
+save_steps: 6250
+save_total_limit: 1
+report_to: none
+
+seed: 42
+
+accelerator_config:
+  dispatch_batches: false
+  split_batches: false

hruska_10_experiments_results/hruska_10_experiments_results/10_r16_a32_lr1e4/10_r16_a32_lr1e4.yaml

@@ -0,0 +1,64 @@
+stage: sft
+do_train: true
+do_eval: true
+
+model_name_or_path: slovak-nlp/mistral-sk-7b
+trust_remote_code: true
+
+dataset_dir: data
+dataset: aya_slovak_100k_fixed
+template: alpaca
+cutoff_len: 1024
+packing: false
+train_on_prompt: false
+
+finetuning_type: lora
+lora_rank: 16
+lora_alpha: 32
+lora_dropout: 0.0
+lora_target: q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj
+
+per_device_train_batch_size: 1
+per_device_eval_batch_size: 1
+gradient_accumulation_steps: 8
+
+learning_rate: 0.0001
+lr_scheduler_type: cosine
+warmup_steps: 500
+max_grad_norm: 0.5
+
+bf16: true
+fp16: false
+optim: adamw_torch
+flash_attn: auto
+plot_loss: true
+
+ddp_timeout: 180000000
+ddp_find_unused_parameters: false
+include_num_input_tokens_seen: true
+enable_thinking: false
+
+use_unsloth: true
+use_unsloth_gc: true
+
+streaming: false
+max_steps: 6250
+
+eval_strategy: steps
+val_size: 1000
+eval_steps: 1250
+
+overwrite_cache: false
+overwrite_output_dir: true
+output_dir: /home/schwarc/diplomovka/hruska_compare9_100k_fixed_10_r16_a32_lr1e4
+
+logging_steps: 50
+save_steps: 6250
+save_total_limit: 1
+report_to: none
+
+seed: 42
+
+accelerator_config:
+  dispatch_batches: false
+  split_batches: false

hruska_10_experiments_results/hruska_experiment_summary.csv

@@ -0,0 +1,11 @@
+rank,experiment,eval_loss,train_loss,train_runtime
+1,10_r16_a32_lr1e4,0.6918,0.8612,7:15:07.38
+2,06_lr1e4_r16_a16,0.7184,0.889,7:17:30.28
+3,04_rank32_a32_lr5e5,0.7292,0.9003,7:22:32.83
+4,05_r16_alpha32_lr5e5,0.7323,0.9026,7:17:43.75
+5,02_optimizer_adamw8bit_r16_a16_lr5e5,0.7521,0.9248,7:20:23.21
+6,09_batch2_accum4_r16_a16_lr5e5,0.7563,0.929,8:24:57.09
+7,01_baseline_r16_a16_lr5e5_adamw,0.7567,0.929,7:18:05.66
+8,03_rank8_a16_lr5e5,0.7586,0.9308,7:16:23.07
+9,07_lr2e5_r16_a16,0.7912,0.9674,7:18:24.50
+10,08_attention_only_r16_a16_lr5e5,0.8094,0.9808,6:51:24.56