Upload LoRA adapter for CLI completion

.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-45/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-49/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,124 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: Qwen/Qwen2-0.5B
+tags:
+- axolotl
+- base_model:adapter:Qwen/Qwen2-0.5B
+- lora
+- transformers
+- cli
+- zsh
+- command-completion
+pipeline_tag: text-generation
+---
+
+<!-- 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. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.13.1`
+```yaml
+base_model: Qwen/Qwen2-0.5B
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+trust_remote_code: true
+datasets:
+- path: /Users/duoyun/Desktop/zsh-llm-cli-autocomplete-tool/src/training/data_splits_axolotl/train_axolotl.jsonl
+  type: alpaca
+dataset_prepared_path: /Users/duoyun/Desktop/zsh-llm-cli-autocomplete-tool/last_run_prepared
+val_set_size: 0.0
+output_dir: /Users/duoyun/Desktop/zsh-llm-cli-autocomplete-tool/zsh-lora-output
+adapter: lora
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+- q_proj
+- k_proj
+- v_proj
+- o_proj
+- gate_proj
+- up_proj
+- down_proj
+lora_modules_to_save:
+- embed_tokens
+- lm_head
+sequence_len: 512
+sample_packing: false
+pad_to_sequence_len: true
+micro_batch_size: 1
+gradient_accumulation_steps: 8
+num_epochs: 2
+optimizer: adamw_torch
+lr_scheduler: cosine
+learning_rate: 0.0002
+warmup_steps: 50
+load_in_8bit: false
+load_in_4bit: true
+bf16: false
+fp16: false
+tf32: false
+gradient_checkpointing: true
+group_by_length: false
+logging_steps: 10
+save_steps: 15
+save_safetensors: true
+save_total_limit: 2
+early_stopping_patience: null
+early_stopping_threshold: null
+wandb_mode: disabled
+fp8: false
+val_dataset:
+  path: /Users/duoyun/Desktop/zsh-llm-cli-autocomplete-tool/src/training/data_splits_axolotl/val_axolotl.jsonl
+  type: alpaca
+
+```
+
+</details><br>
+
+# Users/duoyun/Desktop/zsh-llm-cli-autocomplete-tool/zsh-lora-output
+
+This model is a fine-tuned version of [Qwen/Qwen2-0.5B](https://huggingface.co/Qwen/Qwen2-0.5B) on the /Users/duoyun/Desktop/zsh-llm-cli-autocomplete-tool/src/training/data_splits_axolotl/train_axolotl.jsonl dataset.
+
+## 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: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- 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: 50
+- training_steps: 49
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.18.1
+- Transformers 4.57.6
+- Pytorch 2.10.0
+- Datasets 4.5.0
+- Tokenizers 0.22.1

adapter_config.json

@@ -0,0 +1,49 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-0.5B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": [],
+  "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 sha256:2afafe383fd3070d656b773302c6b4e0623cce20bdbbb5e205a5a01c6c8cf36a
+size 1106719360

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-45/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen2-0.5B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:Qwen/Qwen2-0.5B
+- 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-45/adapter_config.json

@@ -0,0 +1,49 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-0.5B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-45/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaea36deba4e0e785ca79e38120268a551f7d763ffca95542b54e178d1666c87
+size 1106719360

checkpoint-45/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

checkpoint-45/chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-45/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25a4d79a175f1a89c810ddc690b8b04a847cb8c4310ff2444f8842ecf29a8d35
+size 2213621849

checkpoint-45/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3a77d4a8b98ce027a4d6a3b9fb5d7c904e27ec1efd5c0468c24fa26bb738316
+size 14455

checkpoint-45/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:451a1b14856da9cbd260e713e9fe3042640631bba6b72c249525f81b7cded72f
+size 1465

checkpoint-45/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-45/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

checkpoint-45/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-45/tokens_state.

@@ -0,0 +1 @@
+{"total": 181248, "trainable": 3034}

checkpoint-45/trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.824742268041237,
+  "eval_steps": 500,
+  "global_step": 45,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.41237113402061853,
+      "grad_norm": 29.422929763793945,
+      "learning_rate": 3.6e-05,
+      "loss": 2.1003,
+      "memory/device_reserved (GiB)": 0,
+      "memory/max_active (GiB)": 4.94,
+      "memory/max_allocated (GiB)": 8.44,
+      "ppl": 8.16862,
+      "step": 10,
+      "tokens/total": 40960,
+      "tokens/train_per_sec_per_gpu": 0.03,
+      "tokens/trainable": 732
+    },
+    {
+      "epoch": 0.8247422680412371,
+      "grad_norm": 20.819232940673828,
+      "learning_rate": 7.6e-05,
+      "loss": 1.3313,
+      "memory/device_reserved (GiB)": 0,
+      "memory/max_active (GiB)": 4.94,
+      "memory/max_allocated (GiB)": 8.44,
+      "ppl": 3.78596,
+      "step": 20,
+      "tokens/total": 81920,
+      "tokens/train_per_sec_per_gpu": 0.01,
+      "tokens/trainable": 1375
+    },
+    {
+      "epoch": 1.2061855670103092,
+      "grad_norm": 10.385747909545898,
+      "learning_rate": 0.000116,
+      "loss": 0.8107,
+      "memory/device_reserved (GiB)": 0,
+      "memory/max_active (GiB)": 4.94,
+      "memory/max_allocated (GiB)": 8.44,
+      "ppl": 2.24948,
+      "step": 30,
+      "tokens/total": 119808,
+      "tokens/train_per_sec_per_gpu": 0.03,
+      "tokens/trainable": 1990
+    },
+    {
+      "epoch": 1.6185567010309279,
+      "grad_norm": 9.247703552246094,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.4243,
+      "memory/device_reserved (GiB)": 0,
+      "memory/max_active (GiB)": 4.94,
+      "memory/max_allocated (GiB)": 8.44,
+      "ppl": 1.52852,
+      "step": 40,
+      "tokens/total": 160768,
+      "tokens/train_per_sec_per_gpu": 0.01,
+      "tokens/trainable": 2671
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 49,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 15,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 542038679617536.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-45/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:434943d8bfb0e6ab241b45e97b35fe0a388267c99b5de4d3c9271d0ff99b8a2a
+size 7377

checkpoint-49/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen2-0.5B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:Qwen/Qwen2-0.5B
+- 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-49/adapter_config.json

@@ -0,0 +1,49 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-0.5B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-49/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2afafe383fd3070d656b773302c6b4e0623cce20bdbbb5e205a5a01c6c8cf36a
+size 1106719360

checkpoint-49/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

checkpoint-49/chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-49/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80489d448ce2535256b918ddf39a044884a048b784f560de4bdabe2d269eff82
+size 2213621849

checkpoint-49/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3a77d4a8b98ce027a4d6a3b9fb5d7c904e27ec1efd5c0468c24fa26bb738316
+size 14455

checkpoint-49/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee69f4a1ef41348da5c66cb68420149fa18a869bb5f1f8c8e413d37c2db0166d
+size 1465

checkpoint-49/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-49/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

checkpoint-49/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-49/tokens_state.

@@ -0,0 +1 @@
+{"total": 197632, "trainable": 3290}

checkpoint-49/trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9896907216494846,
+  "eval_steps": 500,
+  "global_step": 49,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.41237113402061853,
+      "grad_norm": 29.422929763793945,
+      "learning_rate": 3.6e-05,
+      "loss": 2.1003,
+      "memory/device_reserved (GiB)": 0,
+      "memory/max_active (GiB)": 4.94,
+      "memory/max_allocated (GiB)": 8.44,
+      "ppl": 8.16862,
+      "step": 10,
+      "tokens/total": 40960,
+      "tokens/train_per_sec_per_gpu": 0.03,
+      "tokens/trainable": 732
+    },
+    {
+      "epoch": 0.8247422680412371,
+      "grad_norm": 20.819232940673828,
+      "learning_rate": 7.6e-05,
+      "loss": 1.3313,
+      "memory/device_reserved (GiB)": 0,
+      "memory/max_active (GiB)": 4.94,
+      "memory/max_allocated (GiB)": 8.44,
+      "ppl": 3.78596,
+      "step": 20,
+      "tokens/total": 81920,
+      "tokens/train_per_sec_per_gpu": 0.01,
+      "tokens/trainable": 1375
+    },
+    {
+      "epoch": 1.2061855670103092,
+      "grad_norm": 10.385747909545898,
+      "learning_rate": 0.000116,
+      "loss": 0.8107,
+      "memory/device_reserved (GiB)": 0,
+      "memory/max_active (GiB)": 4.94,
+      "memory/max_allocated (GiB)": 8.44,
+      "ppl": 2.24948,
+      "step": 30,
+      "tokens/total": 119808,
+      "tokens/train_per_sec_per_gpu": 0.03,
+      "tokens/trainable": 1990
+    },
+    {
+      "epoch": 1.6185567010309279,
+      "grad_norm": 9.247703552246094,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.4243,
+      "memory/device_reserved (GiB)": 0,
+      "memory/max_active (GiB)": 4.94,
+      "memory/max_allocated (GiB)": 8.44,
+      "ppl": 1.52852,
+      "step": 40,
+      "tokens/total": 160768,
+      "tokens/train_per_sec_per_gpu": 0.01,
+      "tokens/trainable": 2671
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 49,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 15,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 591036526362624.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-49/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:434943d8bfb0e6ab241b45e97b35fe0a388267c99b5de4d3c9271d0ff99b8a2a
+size 7377

config.json

@@ -0,0 +1,53 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "float32",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

debug.log

@@ -0,0 +1,201 @@
+[2026-02-21 20:37:21,574] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:5467] baseline 0.000GB (+0.000GB allocated)
+[2026-02-21 20:37:21,574] [INFO] [axolotl.cli.config.load_cfg:259] [PID:5467] config:
+{
+  "activation_offloading": false,
+  "adapter": "lora",
+  "axolotl_config_path": "src/training/qwen3_axolotl_config.yml",
+  "base_model": "Qwen/Qwen2-0.5B",
+  "base_model_config": "Qwen/Qwen2-0.5B",
+  "batch_size": 8,
+  "bf16": false,
+  "capabilities": {
+    "bf16": true,
+    "fp8": false,
+    "n_gpu": 1,
+    "n_node": 1
+  },
+  "context_parallel_size": 1,
+  "dataloader_num_workers": 1,
+  "dataloader_pin_memory": true,
+  "dataloader_prefetch_factor": 256,
+  "dataset_num_proc": 8,
+  "dataset_prepared_path": "/Users/duoyun/Desktop/zsh-llm-cli-autocomplete-tool/last_run_prepared",
+  "datasets": [
+    {
+      "message_property_mappings": {
+        "content": "content",
+        "role": "role"
+      },
+      "path": "/Users/duoyun/Desktop/zsh-llm-cli-autocomplete-tool/src/training/data_splits_axolotl/train_axolotl.jsonl",
+      "trust_remote_code": false,
+      "type": "alpaca"
+    }
+  ],
+  "ddp": false,
+  "device": "mps",
+  "dion_rank_fraction": 1.0,
+  "dion_rank_multiple_of": 1,
+  "env_capabilities": {
+    "torch_version": "2.10.0"
+  },
+  "eval_batch_size": 1,
+  "eval_causal_lm_metrics": [
+    "sacrebleu",
+    "comet",
+    "ter",
+    "chrf"
+  ],
+  "eval_max_new_tokens": 128,
+  "eval_table_size": 0,
+  "experimental_skip_move_to_device": true,
+  "fp16": false,
+  "fp8": false,
+  "gradient_accumulation_steps": 8,
+  "gradient_checkpointing": true,
+  "gradient_checkpointing_kwargs": {
+    "use_reentrant": true
+  },
+  "group_by_length": false,
+  "include_tkps": true,
+  "is_falcon_derived_model": false,
+  "is_llama_derived_model": false,
+  "is_mistral_derived_model": false,
+  "learning_rate": 0.0002,
+  "lisa_layers_attribute": "model.layers",
+  "load_best_model_at_end": false,
+  "load_in_4bit": true,
+  "load_in_8bit": false,
+  "local_rank": 0,
+  "logging_steps": 10,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "lora_modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "lora_r": 8,
+  "lora_target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "loraplus_lr_embedding": 1e-06,
+  "lr_scheduler": "cosine",
+  "mean_resizing_embeddings": false,
+  "micro_batch_size": 1,
+  "model_config_type": "qwen2",
+  "num_epochs": 2.0,
+  "optimizer": "adamw_torch",
+  "otel_metrics_host": "localhost",
+  "otel_metrics_port": 8000,
+  "output_dir": "/Users/duoyun/Desktop/zsh-llm-cli-autocomplete-tool/zsh-lora-output",
+  "pad_to_sequence_len": true,
+  "pretrain_multipack_attn": true,
+  "profiler_steps_start": 0,
+  "qlora_sharded_model_loading": false,
+  "ray_num_workers": 1,
+  "resources_per_worker": {
+    "GPU": 1
+  },
+  "sample_packing": false,
+  "sample_packing_bin_size": 200,
+  "sample_packing_group_size": 100000,
+  "save_only_model": false,
+  "save_safetensors": true,
+  "save_steps": 15,
+  "save_total_limit": 2,
+  "sequence_len": 512,
+  "shuffle_before_merging_datasets": false,
+  "shuffle_merged_datasets": true,
+  "skip_prepare_dataset": false,
+  "streaming_multipack_buffer_size": 10000,
+  "strict": false,
+  "tensor_parallel_size": 1,
+  "tf32": false,
+  "tiled_mlp_use_original_mlp": true,
+  "tokenizer_config": "Qwen/Qwen2-0.5B",
+  "tokenizer_save_jinja_files": true,
+  "tokenizer_type": "AutoTokenizer",
+  "torch_dtype": "torch.float32",
+  "train_on_inputs": false,
+  "trl": {
+    "log_completions": false,
+    "mask_truncated_completions": false,
+    "ref_model_mixup_alpha": 0.9,
+    "ref_model_sync_steps": 64,
+    "scale_rewards": true,
+    "sync_ref_model": false,
+    "use_vllm": false,
+    "vllm_server_host": "0.0.0.0",
+    "vllm_server_port": 8000
+  },
+  "trust_remote_code": true,
+  "type_of_model": "AutoModelForCausalLM",
+  "use_otel_metrics": false,
+  "use_ray": false,
+  "val_set_size": 0.0,
+  "vllm": {
+    "device": "auto",
+    "dtype": "auto",
+    "gpu_memory_utilization": 0.9,
+    "host": "0.0.0.0",
+    "port": 8000
+  },
+  "wandb_mode": "disabled",
+  "warmup_steps": 50,
+  "weight_decay": 0.0,
+  "world_size": 1
+}
+[2026-02-21 20:37:22,676] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:285] [PID:5467] EOS: 151643 / <|endoftext|>
+[2026-02-21 20:37:22,677] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:286] [PID:5467] BOS: None / None
+[2026-02-21 20:37:22,677] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:287] [PID:5467] PAD: 151643 / <|endoftext|>
+[2026-02-21 20:37:22,677] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:288] [PID:5467] UNK: None / None
+[2026-02-21 20:37:22,679] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:475] [PID:5467] Loading prepared dataset from disk at /Users/duoyun/Desktop/zsh-llm-cli-autocomplete-tool/last_run_prepared/41f31c3c9bc9eb4eb6e943fbbbb74dda...
+[2026-02-21 20:37:22,701] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:417] [PID:5467] total_num_tokens: 12_122
+[2026-02-21 20:37:22,703] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:435] [PID:5467] `total_supervised_tokens: 1_660`
+[2026-02-21 20:37:22,703] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:533] [PID:5467] total_num_steps: 49
+[2026-02-21 20:37:22,703] [INFO] [axolotl.utils.data.sft._prepare_standard_dataset:121] [PID:5467] Maximum number of steps set at 49
+[2026-02-21 20:37:22,735] [DEBUG] [axolotl.train.setup_model_and_tokenizer:70] [PID:5467] loading tokenizer... Qwen/Qwen2-0.5B
+[2026-02-21 20:37:23,594] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:285] [PID:5467] EOS: 151643 / <|endoftext|>
+[2026-02-21 20:37:23,594] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:286] [PID:5467] BOS: None / None
+[2026-02-21 20:37:23,594] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:287] [PID:5467] PAD: 151643 / <|endoftext|>
+[2026-02-21 20:37:23,594] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:288] [PID:5467] UNK: None / None
+[2026-02-21 20:37:23,594] [DEBUG] [axolotl.train.setup_model_and_tokenizer:82] [PID:5467] Loading model
+[2026-02-21 20:37:23,742] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_evaluation_loop:87] [PID:5467] Patched Trainer.evaluation_loop with nanmean loss calculation
+[2026-02-21 20:37:23,744] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_maybe_log_save_evaluate:138] [PID:5467] Patched Trainer._maybe_log_save_evaluate with nanmean loss calculation
+[2026-02-21 20:37:23,752] [WARNING] [transformers.modeling_utils.warning_once:328] [PID:5467] `torch_dtype` is deprecated! Use `dtype` instead!
+[2026-02-21 20:37:27,045] [INFO] [axolotl.loaders.model._prepare_model_for_quantization:853] [PID:5467] converting PEFT model w/ prepare_model_for_kbit_training
+[2026-02-21 20:37:27,047] [INFO] [axolotl.loaders.model._configure_embedding_dtypes:347] [PID:5467] Converting modules to torch.float32
+[2026-02-21 20:37:27,049] [DEBUG] [axolotl.loaders.model.log_gpu_memory_usage:127] [PID:5467] Memory usage after model load 0.000GB (+0.000GB allocated)
+[2026-02-21 20:37:27,053] [WARNING] [py.warnings._showwarnmsg:110] [PID:5467] /Users/duoyun/Desktop/zsh-llm-cli-autocomplete-tool/venv/lib/python3.13/site-packages/peft/tuners/tuners_utils.py:1225: UserWarning: Model has `tie_word_embeddings=True` and a tied layer is part of the adapter, but `ensure_weight_tying` is not set to True. This can lead to complications, for example when merging the adapter or converting your model to formats other than safetensors. Check the discussion here: https://github.com/huggingface/peft/issues/2777
+  warnings.warn(msg)
+
+trainable params: 276,668,416 || all params: 770,701,184 || trainable%: 35.8983
+[2026-02-21 20:37:27,656] [DEBUG] [axolotl.loaders.model.log_gpu_memory_usage:127] [PID:5467] after adapters 0.000GB (+0.000GB allocated)
+[2026-02-21 20:37:33,551] [INFO] [axolotl.train.save_initial_configs:413] [PID:5467] Pre-saving adapter config to /Users/duoyun/Desktop/zsh-llm-cli-autocomplete-tool/zsh-lora-output...
+[2026-02-21 20:37:33,553] [INFO] [axolotl.train.save_initial_configs:417] [PID:5467] Pre-saving tokenizer to /Users/duoyun/Desktop/zsh-llm-cli-autocomplete-tool/zsh-lora-output...
+[2026-02-21 20:37:33,733] [INFO] [axolotl.train.save_initial_configs:422] [PID:5467] Pre-saving model config to /Users/duoyun/Desktop/zsh-llm-cli-autocomplete-tool/zsh-lora-output...
+[2026-02-21 20:37:33,737] [INFO] [axolotl.train.execute_training:212] [PID:5467] Starting trainer...
+[2026-02-21 20:37:33,737] [WARNING] [transformers.trainer._align_special_tokens:982] [PID:5467] The tokenizer has new PAD/BOS/EOS tokens that differ from the model config and generation config. The model config and generation config were aligned accordingly, being updated with the tokenizer's values. Updated tokens: {'bos_token_id': None, 'pad_token_id': 151643}.
+
  0%|          | 0/49 [00:00<?, ?it/s][2026-02-21 20:37:34,099] [WARNING] [py.warnings._showwarnmsg:110] [PID:5467] /Users/duoyun/Desktop/zsh-llm-cli-autocomplete-tool/venv/lib/python3.13/site-packages/torch/utils/data/dataloader.py:1118: UserWarning: 'pin_memory' argument is set as true but not supported on MPS now, device pinned memory won't be used.
+  super().__init__(loader)
+
+
  2%|▏         | 1/49 [00:49<39:37, 49.52s/it]
  4%|▍         | 2/49 [01:38<38:45, 49.48s/it]
  6%|▌         | 3/49 [02:39<41:49, 54.56s/it]
  8%|▊         | 4/49 [03:19<36:40, 48.90s/it]
 10%|█         | 5/49 [04:06<35:15, 48.07s/it]
 12%|█▏        | 6/49 [04:46<32:31, 45.39s/it]
 14%|█▍        | 7/49 [05:33<32:04, 45.82s/it]
 16%|█▋        | 8/49 [06:19<31:27, 46.03s/it]
 18%|█▊        | 9/49 [06:59<29:27, 44.20s/it]
 20%|██        | 10/49 [07:39<27:45, 42.71s/it]
                                               
+
 20%|██        | 10/49 [07:43<27:45, 42.71s/it]
 22%|██▏       | 11/49 [08:20<26:48, 42.33s/it]
 24%|██▍       | 12/49 [09:11<27:37, 44.80s/it]
 27%|██▋       | 13/49 [09:56<27:02, 45.07s/it]
 29%|██▊       | 14/49 [10:45<26:55, 46.15s/it]
 31%|███       | 15/49 [11:29<25:49, 45.58s/it][2026-02-21 20:49:03,976] [INFO] [axolotl.core.trainers.base._save:721] [PID:5467] Saving model checkpoint to /Users/duoyun/Desktop/zsh-llm-cli-autocomplete-tool/zsh-lora-output/checkpoint-15
+
 33%|███▎      | 16/49 [12:34<28:15, 51.37s/it]
 35%|███▍      | 17/49 [13:17<26:04, 48.90s/it]
 37%|███▋      | 18/49 [14:01<24:26, 47.32s/it]
 39%|███▉      | 19/49 [14:52<24:09, 48.31s/it]
 41%|████      | 20/49 [15:42<23:36, 48.83s/it]
                                               
+
 41%|████      | 20/49 [15:47<23:36, 48.83s/it]
 43%|████▎     | 21/49 [16:32<22:58, 49.25s/it]
 45%|████▍     | 22/49 [17:12<20:53, 46.42s/it]
 47%|████▋     | 23/49 [17:55<19:46, 45.63s/it]
 49%|████▉     | 24/49 [18:36<18:24, 44.19s/it]
 51%|█████     | 25/49 [19:00<15:11, 37.96s/it][2026-02-21 20:56:34,355] [WARNING] [py.warnings._showwarnmsg:110] [PID:5467] /Users/duoyun/Desktop/zsh-llm-cli-autocomplete-tool/venv/lib/python3.13/site-packages/torch/utils/data/dataloader.py:1118: UserWarning: 'pin_memory' argument is set as true but not supported on MPS now, device pinned memory won't be used.
+  super().__init__(loader)
+
+
 53%|█████▎    | 26/49 [19:50<16:01, 41.81s/it]
 55%|█████▌    | 27/49 [20:32<15:20, 41.84s/it]
 57%|█████▋    | 28/49 [21:19<15:08, 43.24s/it]
 59%|█████▉    | 29/49 [22:10<15:13, 45.67s/it]
 61%|██████    | 30/49 [23:16<16:22, 51.72s/it]
                                               
+
 61%|██████    | 30/49 [23:22<16:22, 51.72s/it][2026-02-21 21:00:56,360] [INFO] [axolotl.core.trainers.base._save:721] [PID:5467] Saving model checkpoint to /Users/duoyun/Desktop/zsh-llm-cli-autocomplete-tool/zsh-lora-output/checkpoint-30
+
 63%|██████▎   | 31/49 [24:24<16:58, 56.56s/it]
 65%|██████▌   | 32/49 [25:20<16:00, 56.51s/it]
 67%|██████▋   | 33/49 [26:27<15:51, 59.48s/it]
 69%|██████▉   | 34/49 [27:21<14:26, 57.79s/it]
 71%|███████▏  | 35/49 [28:10<12:52, 55.20s/it]
 73%|███████▎  | 36/49 [28:50<11:00, 50.77s/it]
 76%|███████▌  | 37/49 [29:32<09:37, 48.10s/it]
 78%|███████▊  | 38/49 [30:19<08:46, 47.83s/it]
 80%|███████▉  | 39/49 [31:07<07:57, 47.79s/it]
 82%|████████▏ | 40/49 [31:54<07:07, 47.45s/it]
                                               
+
 82%|████████▏ | 40/49 [31:59<07:07, 47.45s/it]
 84%|████████▎ | 41/49 [33:01<07:06, 53.31s/it]
 86%|████████▌ | 42/49 [33:56<06:17, 53.91s/it]
 88%|████████▊ | 43/49 [34:57<05:35, 55.99s/it]
 90%|████████▉ | 44/49 [35:49<04:34, 54.85s/it]
 92%|█████████▏| 45/49 [36:49<03:45, 56.49s/it][2026-02-21 21:14:23,862] [INFO] [axolotl.core.trainers.base._save:721] [PID:5467] Saving model checkpoint to /Users/duoyun/Desktop/zsh-llm-cli-autocomplete-tool/zsh-lora-output/checkpoint-45
+
 94%|█████████▍| 46/49 [38:04<03:05, 61.88s/it]
 96%|█████████▌| 47/49 [38:53<01:56, 58.24s/it]
 98%|█████████▊| 48/49 [39:49<00:57, 57.40s/it]
+
                                               
+
+[2026-02-21 21:18:29,199] [INFO] [axolotl.train.save_trained_model:233] [PID:5467] Training completed! Saving trained model to /Users/duoyun/Desktop/zsh-llm-cli-autocomplete-tool/zsh-lora-output.
+[2026-02-21 21:18:31,934] [INFO] [axolotl.train.save_trained_model:351] [PID:5467] Model successfully saved to /Users/duoyun/Desktop/zsh-llm-cli-autocomplete-tool/zsh-lora-output

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}