Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-126/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-189/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,62 @@
+---
+base_model: MLP-KTLim/llama-3-Korean-Bllossom-8B
+library_name: peft
+model_name: lora-output
+tags:
+- base_model:adapter:MLP-KTLim/llama-3-Korean-Bllossom-8B
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for lora-output
+
+This model is a fine-tuned version of [MLP-KTLim/llama-3-Korean-Bllossom-8B](https://huggingface.co/MLP-KTLim/llama-3-Korean-Bllossom-8B).
+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
+
+ 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.18.1
+- TRL: 1.0.0
+- Transformers: 5.0.0
+- Pytorch: 2.10.0+cu128
+- Datasets: 4.8.4
+- 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}
+}
+```

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "MLP-KTLim/llama-3-Korean-Bllossom-8B",
+  "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",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b66eff5c492c20896e122c211b3afed8df9f88e372c1b1ce643a3ee61c564e
+size 83946192

chat_template.jinja

@@ -0,0 +1,5 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
+
+'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
+
+' }}{% endif %}

checkpoint-126/README.md

@@ -0,0 +1,209 @@
+---
+base_model: MLP-KTLim/llama-3-Korean-Bllossom-8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:MLP-KTLim/llama-3-Korean-Bllossom-8B
+- 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 0.18.1

checkpoint-126/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "MLP-KTLim/llama-3-Korean-Bllossom-8B",
+  "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",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-126/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f31d67ca5ebe41a785f6ed38976f861f71719c75f78b2076c44a243cd4c6a0de
+size 83946192

checkpoint-126/chat_template.jinja

@@ -0,0 +1,5 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
+
+'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
+
+' }}{% endif %}

checkpoint-126/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2ffe81f13727b15aac3e708ebebb1d1698a5829bd73784326edbad946a8c0ba
+size 168156963

checkpoint-126/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea7648bd3cada29f669a451e62cc2d817fb89e5d33c1e3ea5ad13070a76bce18
+size 14645

checkpoint-126/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e26ff6f44108cb1259f5414ce913a00399cba9468c18c8bb4f25b409a251d6c9
+size 1465

checkpoint-126/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2539802b4016767e5475c0fa774895f4c33683f7c2ed9df643a61279e9ef1bd2
+size 17209962

checkpoint-126/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "is_local": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "TokenizersBackend"
+}

checkpoint-126/trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 126,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.683317294716835,
+      "epoch": 0.16,
+      "grad_norm": 1.25,
+      "learning_rate": 0.00019047619047619048,
+      "loss": 1.564039134979248,
+      "mean_token_accuracy": 0.6754204630851746,
+      "num_tokens": 40830.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.9686750799417496,
+      "epoch": 0.32,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.0001798941798941799,
+      "loss": 0.7677403450012207,
+      "mean_token_accuracy": 0.8253099352121354,
+      "num_tokens": 81397.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.5634016528725624,
+      "epoch": 0.48,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.00016931216931216931,
+      "loss": 0.3984677791595459,
+      "mean_token_accuracy": 0.9086249053478241,
+      "num_tokens": 122149.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.33716473132371905,
+      "epoch": 0.64,
+      "grad_norm": 0.83984375,
+      "learning_rate": 0.00015873015873015873,
+      "loss": 0.20998120307922363,
+      "mean_token_accuracy": 0.9537941217422485,
+      "num_tokens": 162266.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.18942079581320287,
+      "epoch": 0.8,
+      "grad_norm": 0.625,
+      "learning_rate": 0.00014814814814814815,
+      "loss": 0.12097519636154175,
+      "mean_token_accuracy": 0.9719412356615067,
+      "num_tokens": 203396.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.15256804414093494,
+      "epoch": 0.96,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00013756613756613756,
+      "loss": 0.09078920483589173,
+      "mean_token_accuracy": 0.9763795837759972,
+      "num_tokens": 244017.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.10731093036501031,
+      "epoch": 1.112,
+      "grad_norm": 0.3046875,
+      "learning_rate": 0.00012698412698412698,
+      "loss": 0.0671606719493866,
+      "mean_token_accuracy": 0.9821337900663677,
+      "num_tokens": 283322.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.08502924609929323,
+      "epoch": 1.272,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.0001164021164021164,
+      "loss": 0.05377537608146667,
+      "mean_token_accuracy": 0.9846220448613167,
+      "num_tokens": 323890.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.07848603706806898,
+      "epoch": 1.432,
+      "grad_norm": 0.294921875,
+      "learning_rate": 0.00010582010582010582,
+      "loss": 0.0482613205909729,
+      "mean_token_accuracy": 0.9856140300631523,
+      "num_tokens": 364334.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.07067316640168428,
+      "epoch": 1.592,
+      "grad_norm": 0.38671875,
+      "learning_rate": 9.523809523809524e-05,
+      "loss": 0.045552247762680055,
+      "mean_token_accuracy": 0.9858392000198364,
+      "num_tokens": 405030.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.06471487935632467,
+      "epoch": 1.752,
+      "grad_norm": 0.2890625,
+      "learning_rate": 8.465608465608466e-05,
+      "loss": 0.042380091547966,
+      "mean_token_accuracy": 0.9858248203992843,
+      "num_tokens": 445985.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.05875909021124244,
+      "epoch": 1.912,
+      "grad_norm": 0.322265625,
+      "learning_rate": 7.407407407407407e-05,
+      "loss": 0.037678882479667664,
+      "mean_token_accuracy": 0.9872250691056251,
+      "num_tokens": 486256.0,
+      "step": 120
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 189,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 2.408299068058829e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-126/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:788cfacc8f409ca64ed43ed4e14805f5a927e0e525729f7f5fef2ecc875d52d8
+size 5649

checkpoint-189/README.md

@@ -0,0 +1,209 @@
+---
+base_model: MLP-KTLim/llama-3-Korean-Bllossom-8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:MLP-KTLim/llama-3-Korean-Bllossom-8B
+- 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 0.18.1

checkpoint-189/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "MLP-KTLim/llama-3-Korean-Bllossom-8B",
+  "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",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-189/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b66eff5c492c20896e122c211b3afed8df9f88e372c1b1ce643a3ee61c564e
+size 83946192

checkpoint-189/chat_template.jinja

@@ -0,0 +1,5 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
+
+'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
+
+' }}{% endif %}

checkpoint-189/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97f9e6e52f9d0ff61bce747d7d292075f7a8df083a15eb4c7c98b36a7b5556c5
+size 168156963

checkpoint-189/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5775a7826b0439c1ea9f5b2cd8ff944c0e55c77c825cd6d06f5c24bd1d719794
+size 14645

checkpoint-189/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8e34da48af5828bc3fc98b44a01324f3c94032c4634909cd84c58666c877303
+size 1465

checkpoint-189/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2539802b4016767e5475c0fa774895f4c33683f7c2ed9df643a61279e9ef1bd2
+size 17209962

checkpoint-189/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "is_local": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "TokenizersBackend"
+}

checkpoint-189/trainer_state.json

@@ -0,0 +1,214 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 189,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.683317294716835,
+      "epoch": 0.16,
+      "grad_norm": 1.25,
+      "learning_rate": 0.00019047619047619048,
+      "loss": 1.564039134979248,
+      "mean_token_accuracy": 0.6754204630851746,
+      "num_tokens": 40830.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.9686750799417496,
+      "epoch": 0.32,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.0001798941798941799,
+      "loss": 0.7677403450012207,
+      "mean_token_accuracy": 0.8253099352121354,
+      "num_tokens": 81397.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.5634016528725624,
+      "epoch": 0.48,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.00016931216931216931,
+      "loss": 0.3984677791595459,
+      "mean_token_accuracy": 0.9086249053478241,
+      "num_tokens": 122149.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.33716473132371905,
+      "epoch": 0.64,
+      "grad_norm": 0.83984375,
+      "learning_rate": 0.00015873015873015873,
+      "loss": 0.20998120307922363,
+      "mean_token_accuracy": 0.9537941217422485,
+      "num_tokens": 162266.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.18942079581320287,
+      "epoch": 0.8,
+      "grad_norm": 0.625,
+      "learning_rate": 0.00014814814814814815,
+      "loss": 0.12097519636154175,
+      "mean_token_accuracy": 0.9719412356615067,
+      "num_tokens": 203396.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.15256804414093494,
+      "epoch": 0.96,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00013756613756613756,
+      "loss": 0.09078920483589173,
+      "mean_token_accuracy": 0.9763795837759972,
+      "num_tokens": 244017.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.10731093036501031,
+      "epoch": 1.112,
+      "grad_norm": 0.3046875,
+      "learning_rate": 0.00012698412698412698,
+      "loss": 0.0671606719493866,
+      "mean_token_accuracy": 0.9821337900663677,
+      "num_tokens": 283322.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.08502924609929323,
+      "epoch": 1.272,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.0001164021164021164,
+      "loss": 0.05377537608146667,
+      "mean_token_accuracy": 0.9846220448613167,
+      "num_tokens": 323890.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.07848603706806898,
+      "epoch": 1.432,
+      "grad_norm": 0.294921875,
+      "learning_rate": 0.00010582010582010582,
+      "loss": 0.0482613205909729,
+      "mean_token_accuracy": 0.9856140300631523,
+      "num_tokens": 364334.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.07067316640168428,
+      "epoch": 1.592,
+      "grad_norm": 0.38671875,
+      "learning_rate": 9.523809523809524e-05,
+      "loss": 0.045552247762680055,
+      "mean_token_accuracy": 0.9858392000198364,
+      "num_tokens": 405030.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.06471487935632467,
+      "epoch": 1.752,
+      "grad_norm": 0.2890625,
+      "learning_rate": 8.465608465608466e-05,
+      "loss": 0.042380091547966,
+      "mean_token_accuracy": 0.9858248203992843,
+      "num_tokens": 445985.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.05875909021124244,
+      "epoch": 1.912,
+      "grad_norm": 0.322265625,
+      "learning_rate": 7.407407407407407e-05,
+      "loss": 0.037678882479667664,
+      "mean_token_accuracy": 0.9872250691056251,
+      "num_tokens": 486256.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.053186047234033286,
+      "epoch": 2.064,
+      "grad_norm": 0.2138671875,
+      "learning_rate": 6.349206349206349e-05,
+      "loss": 0.035448721051216124,
+      "mean_token_accuracy": 0.9876284630675065,
+      "num_tokens": 525704.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.048862133827060464,
+      "epoch": 2.224,
+      "grad_norm": 0.1875,
+      "learning_rate": 5.291005291005291e-05,
+      "loss": 0.031160187721252442,
+      "mean_token_accuracy": 0.9887946531176567,
+      "num_tokens": 565962.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.04646068625152111,
+      "epoch": 2.384,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 4.232804232804233e-05,
+      "loss": 0.02885039746761322,
+      "mean_token_accuracy": 0.9891349792480468,
+      "num_tokens": 606585.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.045240774657577275,
+      "epoch": 2.544,
+      "grad_norm": 0.197265625,
+      "learning_rate": 3.1746031746031745e-05,
+      "loss": 0.029539498686790466,
+      "mean_token_accuracy": 0.9894381672143936,
+      "num_tokens": 647738.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.04430276220664382,
+      "epoch": 2.7039999999999997,
+      "grad_norm": 0.2001953125,
+      "learning_rate": 2.1164021164021164e-05,
+      "loss": 0.02942884564399719,
+      "mean_token_accuracy": 0.9888082027435303,
+      "num_tokens": 688939.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.04506665170192718,
+      "epoch": 2.864,
+      "grad_norm": 0.1904296875,
+      "learning_rate": 1.0582010582010582e-05,
+      "loss": 0.02905130386352539,
+      "mean_token_accuracy": 0.9890851527452469,
+      "num_tokens": 729737.0,
+      "step": 180
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 189,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.606892598078669e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-189/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:788cfacc8f409ca64ed43ed4e14805f5a927e0e525729f7f5fef2ecc875d52d8
+size 5649

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2539802b4016767e5475c0fa774895f4c33683f7c2ed9df643a61279e9ef1bd2
+size 17209962

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "is_local": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "TokenizersBackend"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:788cfacc8f409ca64ed43ed4e14805f5a927e0e525729f7f5fef2ecc875d52d8
+size 5649