Upload folder using huggingface_hub

README.md

@@ -0,0 +1,66 @@
+---
+library_name: peft
+license: other
+base_model: MagistrTheOne/KNK-VF-Lab-38B
+tags:
+- base_model:adapter:/workspace/checkpoints/knk_vf_lab_38b
+- llama-factory
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: kurotama-knk-vf-lab38b-lora
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# kurotama-knk-vf-lab38b-lora
+
+This model is a fine-tuned version of [/workspace/checkpoints/knk_vf_lab_38b](https://huggingface.co//workspace/checkpoints/knk_vf_lab_38b) on the kurotama_sharegpt dataset.
+It achieves the following results on the evaluation set:
+- Loss: 8.5199
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.05
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 143.7241      | 1.0   | 29   | 8.5199          |
+
+
+### Framework versions
+
+- PEFT 0.18.1
+- Transformers 5.6.0
+- Pytorch 2.4.1+cu124
+- Datasets 4.0.0
+- Tokenizers 0.22.2

adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "MagistrTheOne/KNK-VF-Lab-38B",
+  "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": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "k_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 sha256:615281d02b129eefc7fc9899f31996c36c1e2523113f07537e1698cb91a18fad
+size 59680720

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 8.519869804382324,
+    "eval_runtime": 12.692,
+    "eval_samples_per_second": 3.152,
+    "eval_steps_per_second": 3.152,
+    "total_flos": 2.9686113589837824e+16,
+    "train_loss": 151.82884058459052,
+    "train_runtime": 802.9271,
+    "train_samples_per_second": 0.573,
+    "train_steps_per_second": 0.036
+}

chat_template.jinja

@@ -0,0 +1,4 @@
+{% 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: ' + system_message + '<|eos|>' + '
+' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '<|eos|>' + '
+Assistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eos|>' + '
+' }}{% endif %}{% endfor %}

checkpoint-29/README.md

@@ -0,0 +1,208 @@
+---
+base_model: /workspace/checkpoints/knk_vf_lab_38b
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/workspace/checkpoints/knk_vf_lab_38b
+- llama-factory
+- lora
+- transformers
+---
+
+# 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-29/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/checkpoints/knk_vf_lab_38b",
+  "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": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-29/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:615281d02b129eefc7fc9899f31996c36c1e2523113f07537e1698cb91a18fad
+size 59680720

checkpoint-29/chat_template.jinja

@@ -0,0 +1,4 @@
+{% 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: ' + system_message + '<|eos|>' + '
+' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '<|eos|>' + '
+Assistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eos|>' + '
+' }}{% endif %}{% endfor %}

checkpoint-29/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c51735337096cdac9dd7eba2e8997cfbed8edd57d0dca4f0c4f8e647aadf4e1b
+size 119543994

checkpoint-29/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbc0913a35ae0f47cb5944d6080985b086f0873ad4df8e7500f026b4d0830afc
+size 14244

checkpoint-29/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77b1cd5ec232ad7fc4a8bf29290c170002b5e29b256da7fe912039052d43ab0b
+size 1064

checkpoint-29/tokenizer_config.json

@@ -0,0 +1,26 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<|bos|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|eos|>",
+  "extra_special_tokens": [
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|tool|>",
+    "<|code|>",
+    "<|/code|>",
+    "<|think|>",
+    "<|/think|>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-29/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 29,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 112.91146087646484,
+      "learning_rate": 8.43120818934367e-05,
+      "loss": 178.4693359375,
+      "step": 10
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 69.01692962646484,
+      "learning_rate": 3.019601169804216e-05,
+      "loss": 143.72413330078126,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 8.519869804382324,
+      "eval_runtime": 12.6349,
+      "eval_samples_per_second": 3.166,
+      "eval_steps_per_second": 3.166,
+      "step": 29
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 29,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.9686113589837824e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-29/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15193b77279cd88f18359fbb0bdcef559f5605db36b4014b868a509ac01198da
+size 5496

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 8.519869804382324,
+    "eval_runtime": 12.692,
+    "eval_samples_per_second": 3.152,
+    "eval_steps_per_second": 3.152
+}

tokenizer_config.json

@@ -0,0 +1,26 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<|bos|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|eos|>",
+  "extra_special_tokens": [
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|tool|>",
+    "<|code|>",
+    "<|/code|>",
+    "<|think|>",
+    "<|/think|>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 2.9686113589837824e+16,
+    "train_loss": 151.82884058459052,
+    "train_runtime": 802.9271,
+    "train_samples_per_second": 0.573,
+    "train_steps_per_second": 0.036
+}

trainer_log.jsonl

@@ -0,0 +1,4 @@
+{"current_steps": 10, "total_steps": 29, "loss": 178.4693359375, "lr": 8.43120818934367e-05, "epoch": 0.34782608695652173, "percentage": 34.48, "elapsed_time": "0:05:10", "remaining_time": "0:09:50"}
+{"current_steps": 20, "total_steps": 29, "loss": 143.72413330078126, "lr": 3.019601169804216e-05, "epoch": 0.6956521739130435, "percentage": 68.97, "elapsed_time": "0:09:27", "remaining_time": "0:04:15"}
+{"current_steps": 29, "total_steps": 29, "eval_loss": 8.519869804382324, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:13:22", "remaining_time": "0:00:00"}
+{"current_steps": 29, "total_steps": 29, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:13:22", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 29,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 112.91146087646484,
+      "learning_rate": 8.43120818934367e-05,
+      "loss": 178.4693359375,
+      "step": 10
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 69.01692962646484,
+      "learning_rate": 3.019601169804216e-05,
+      "loss": 143.72413330078126,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 8.519869804382324,
+      "eval_runtime": 12.6349,
+      "eval_samples_per_second": 3.166,
+      "eval_steps_per_second": 3.166,
+      "step": 29
+    },
+    {
+      "epoch": 1.0,
+      "step": 29,
+      "total_flos": 2.9686113589837824e+16,
+      "train_loss": 151.82884058459052,
+      "train_runtime": 802.9271,
+      "train_samples_per_second": 0.573,
+      "train_steps_per_second": 0.036
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 29,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.9686113589837824e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15193b77279cd88f18359fbb0bdcef559f5605db36b4014b868a509ac01198da
+size 5496