Upload folder using huggingface_hub

https:/huggingface.co/zjc664656505/test_repo/README.md

@@ -0,0 +1,214 @@
+---
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: /GenAI4HW/llama2_13b
+metrics:
+- accuracy
+model-index:
+- name: outputs/llama2-13B-lora-QuArch_0_1_1_alpaca_filtered-answer-context-test-new
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+## General
+# base_model: meta-llama/Meta-Llama-3-8B-Instruct
+base_model: /GenAI4HW/llama2_13b
+# base_model: meta-llama/Llama-2-13b
+model_type: LlamaForCausalLM
+tokenizer_type: AutoTokenizer
+# tokenizer_type: LlamaTokenizer
+output_dir: ./outputs/llama2-13B-lora-QuArch_0_1_1_alpaca_filtered-answer-context-test-new
+seed: 42
+
+## Data Configuration
+datasets:
+  # - path: ./data/QuArch_v0_1_0_alpaca_w_context.json             # With abstract
+  # - path: ./data/QuArch_v0_1_1_alpaca_format.json                # With justification
+  # - path: ./data/QuArch_v0_1_0_alpaca_mmlu.json                  # Without justification
+  - path: ./data/QuArch_v0_1_1_alpaca_filtered_context/ 
+    type: alpaca
+    data_file: train
+    
+dataset_prepared_path:
+
+test_datasets:
+  - path: ./data/QuArch_v0_1_1_alpaca_filtered_context/
+    type: alpaca
+    split: test
+    data_file: 
+        - test  
+  
+  # - path: ./data/QuArch_v0_1_1_alpaca_filtered_context/
+  #   type: alpaca
+  #   split: val
+  #   data_file: 
+  #       - val
+
+## Model Configuration
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+bf16: auto
+fp16:
+tf32: false
+device_map: 'auto'  
+
+## LoRA Configuration
+adapter: lora
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_model_dir:
+lora_fan_in_fan_out:
+
+## Logging Configuration
+logging_dir: ./logs
+logging_steps: 10
+wandb_project: 
+wandb_entity: 
+wandb_watch: 
+wandb_name: 
+wandb_log_model: 
+
+do_eval: true
+## Training Configuration
+sequence_len: 1024
+sample_packing: true
+pad_to_sequence_len: true
+train_on_inputs: false
+group_by_length: false
+micro_batch_size: 1
+gradient_accumulation_steps: 16
+num_epochs: 30
+warmup_steps: 10 
+weight_decay: 0.01
+optimizer: adamw_torch
+lr_scheduler: linear
+learning_rate: 2e-5
+gradient_checkpointing: false
+saves_per_epoch: 1
+# save_steps: 0
+# save_strategy: steps
+save_total_limit: 30
+load_best_model_at_end: true
+greater_is_better: true
+early_stopping_patience:
+resume_from_checkpoint:
+remove_unused_columns: true
+
+## Evaluation Configuration
+eval_sample_packing: False
+eval_batch_size: 1
+evals_per_epoch: 1
+# evaluation_strategy: epoch
+eval_max_new_tokens: 32
+eval_table_size:
+# max_new_token: 32
+# eval_causal_lm_metrics: sacrebleu
+
+# Others
+local_rank: 
+xformers_attention:
+flash_attention: true
+s2_attention:
+debug:
+deepspeed:
+fsdp:
+fsdp_config:
+special_tokens:
+    # pad_token: <|end_of_text|>
+```
+
+</details><br>
+
+# outputs/llama2-13B-lora-QuArch_0_1_1_alpaca_filtered-answer-context-test-new
+
+This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0432
+- Accuracy: 0.9808
+
+## 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: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 32
+- total_eval_batch_size: 2
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 30
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Accuracy |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|
+| No log        | 0.2105  | 1    | 5.1322          | 0.6154   |
+| No log        | 0.8421  | 4    | 5.1271          | 0.6346   |
+| No log        | 1.6842  | 8    | 5.0601          | 0.6538   |
+| 5.1323        | 2.5263  | 12   | 4.7743          | 0.7885   |
+| 5.1323        | 3.3684  | 16   | 4.0491          | 0.9231   |
+| 4.2735        | 4.2105  | 20   | 2.6444          | 0.8846   |
+| 4.2735        | 5.0526  | 24   | 1.0551          | 0.9615   |
+| 4.2735        | 5.8947  | 28   | 0.4698          | 0.6923   |
+| 1.2232        | 6.7368  | 32   | 0.3224          | 0.6731   |
+| 1.2232        | 7.5789  | 36   | 0.2527          | 1.0      |
+| 0.3083        | 8.4211  | 40   | 0.1972          | 1.0      |
+| 0.3083        | 9.2632  | 44   | 0.1372          | 0.9615   |
+| 0.3083        | 10.1053 | 48   | 0.0803          | 1.0      |
+| 0.1761        | 10.9474 | 52   | 0.0575          | 0.9808   |
+| 0.1761        | 11.7895 | 56   | 0.0475          | 0.9808   |
+| 0.116         | 12.6316 | 60   | 0.0444          | 0.9808   |
+| 0.116         | 13.4737 | 64   | 0.0463          | 0.9808   |
+| 0.116         | 14.3158 | 68   | 0.0489          | 0.9808   |
+| 0.0814        | 15.1579 | 72   | 0.0495          | 0.9808   |
+| 0.0814        | 16.0    | 76   | 0.0481          | 0.9808   |
+| 0.0709        | 16.8421 | 80   | 0.0469          | 0.9808   |
+| 0.0709        | 17.6842 | 84   | 0.0457          | 0.9808   |
+| 0.0709        | 18.5263 | 88   | 0.0455          | 0.9808   |
+| 0.0632        | 19.3684 | 92   | 0.0454          | 0.9808   |
+| 0.0632        | 20.2105 | 96   | 0.0459          | 0.9808   |
+| 0.0569        | 21.0526 | 100  | 0.0458          | 0.9808   |
+| 0.0569        | 21.8947 | 104  | 0.0446          | 0.9808   |
+| 0.0569        | 22.7368 | 108  | 0.0451          | 0.9808   |
+| 0.055         | 23.5789 | 112  | 0.0446          | 0.9808   |
+| 0.055         | 24.4211 | 116  | 0.0452          | 0.9808   |
+| 0.0581        | 25.2632 | 120  | 0.0432          | 0.9808   |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.41.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

https:/huggingface.co/zjc664656505/test_repo/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/GenAI4HW/llama2_13b",
+  "bias": "none",
+  "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_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

https:/huggingface.co/zjc664656505/test_repo/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a485ccd9a97977dda43fef1b6f4ff1e9fe34488e04fb00f292e0630f23f6abda
+size 250550026

https:/huggingface.co/zjc664656505/test_repo/checkpoint-36/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: /GenAI4HW/llama2_13b
+---
+
+# 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 0.10.0

https:/huggingface.co/zjc664656505/test_repo/checkpoint-36/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/GenAI4HW/llama2_13b",
+  "bias": "none",
+  "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_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

https:/huggingface.co/zjc664656505/test_repo/checkpoint-36/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea8dee76326dbab5b9ee5649a9beeaff5287686a2876ca9e3b443414a34dc28a
+size 250423448

https:/huggingface.co/zjc664656505/test_repo/checkpoint-36/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:053d10e6415190a1b915ee054b0719d9689ef28562ef0d0a4a600a4821726029
+size 501168482

https:/huggingface.co/zjc664656505/test_repo/checkpoint-36/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd79757612797b5b42a494f5a83f20505477156649867ffb774329d390242a97
+size 14512

https:/huggingface.co/zjc664656505/test_repo/checkpoint-36/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e616603cc235c26fad08aeffee23a01db4ef99c363993b087366dc83f309833
+size 14512

https:/huggingface.co/zjc664656505/test_repo/checkpoint-36/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5661c9efd92d6c32ae5cc18c5220269fd4060e11200b05e1858a9583389f879d
+size 1064

https:/huggingface.co/zjc664656505/test_repo/checkpoint-36/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

https:/huggingface.co/zjc664656505/test_repo/checkpoint-36/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

https:/huggingface.co/zjc664656505/test_repo/checkpoint-36/tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

https:/huggingface.co/zjc664656505/test_repo/checkpoint-36/trainer_state.json

@@ -0,0 +1,144 @@
+{
+  "best_metric": 5.127074241638184,
+  "best_model_checkpoint": "./outputs/llama2-13B-lora-QuArch_0_1_1_alpaca_filtered-answer-context-test-new/checkpoint-4",
+  "epoch": 7.578947368421053,
+  "eval_steps": 4,
+  "global_step": 36,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21052631578947367,
+      "eval_accuracy": 0.6153846153846154,
+      "eval_loss": 5.132209300994873,
+      "eval_runtime": 14.9638,
+      "eval_samples_per_second": 3.475,
+      "eval_steps_per_second": 1.738,
+      "step": 1
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "eval_accuracy": 0.6346153846153846,
+      "eval_loss": 5.127074241638184,
+      "eval_runtime": 15.5565,
+      "eval_samples_per_second": 3.343,
+      "eval_steps_per_second": 1.671,
+      "step": 4
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "eval_accuracy": 0.6538461538461539,
+      "eval_loss": 5.060066223144531,
+      "eval_runtime": 15.7285,
+      "eval_samples_per_second": 3.306,
+      "eval_steps_per_second": 1.653,
+      "step": 8
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 2.453125,
+      "learning_rate": 2e-05,
+      "loss": 5.1323,
+      "step": 10
+    },
+    {
+      "epoch": 2.526315789473684,
+      "eval_accuracy": 0.7884615384615384,
+      "eval_loss": 4.774318695068359,
+      "eval_runtime": 15.4298,
+      "eval_samples_per_second": 3.37,
+      "eval_steps_per_second": 1.685,
+      "step": 12
+    },
+    {
+      "epoch": 3.3684210526315788,
+      "eval_accuracy": 0.9230769230769231,
+      "eval_loss": 4.04908561706543,
+      "eval_runtime": 15.16,
+      "eval_samples_per_second": 3.43,
+      "eval_steps_per_second": 1.715,
+      "step": 16
+    },
+    {
+      "epoch": 4.2105263157894735,
+      "grad_norm": 6.03125,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 4.2735,
+      "step": 20
+    },
+    {
+      "epoch": 4.2105263157894735,
+      "eval_accuracy": 0.8846153846153846,
+      "eval_loss": 2.6443593502044678,
+      "eval_runtime": 15.6094,
+      "eval_samples_per_second": 3.331,
+      "eval_steps_per_second": 1.666,
+      "step": 20
+    },
+    {
+      "epoch": 5.052631578947368,
+      "eval_accuracy": 0.9615384615384616,
+      "eval_loss": 1.0550649166107178,
+      "eval_runtime": 15.8572,
+      "eval_samples_per_second": 3.279,
+      "eval_steps_per_second": 1.64,
+      "step": 24
+    },
+    {
+      "epoch": 5.894736842105263,
+      "eval_accuracy": 0.6923076923076923,
+      "eval_loss": 0.4698377847671509,
+      "eval_runtime": 15.837,
+      "eval_samples_per_second": 3.283,
+      "eval_steps_per_second": 1.642,
+      "step": 28
+    },
+    {
+      "epoch": 6.315789473684211,
+      "grad_norm": 0.6875,
+      "learning_rate": 1.6363636363636366e-05,
+      "loss": 1.2232,
+      "step": 30
+    },
+    {
+      "epoch": 6.7368421052631575,
+      "eval_accuracy": 0.6730769230769231,
+      "eval_loss": 0.3224477767944336,
+      "eval_runtime": 15.7452,
+      "eval_samples_per_second": 3.303,
+      "eval_steps_per_second": 1.651,
+      "step": 32
+    },
+    {
+      "epoch": 7.578947368421053,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.2526957392692566,
+      "eval_runtime": 15.7721,
+      "eval_samples_per_second": 3.297,
+      "eval_steps_per_second": 1.648,
+      "step": 36
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 120,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 4,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.185115697997414e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

https:/huggingface.co/zjc664656505/test_repo/checkpoint-36/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37e0924589b39a0d7454d58ec049450a3b1f1f61ba9617e2608cef4ecdefa104
+size 6072

https:/huggingface.co/zjc664656505/test_repo/checkpoint-40/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: /GenAI4HW/llama2_13b
+---
+
+# 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 0.10.0

https:/huggingface.co/zjc664656505/test_repo/checkpoint-40/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/GenAI4HW/llama2_13b",
+  "bias": "none",
+  "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_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

https:/huggingface.co/zjc664656505/test_repo/checkpoint-40/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e32b8020c15078084a5ba46bd10e69061f19804a3972b84b6a1f40671d6693be
+size 250423448

https:/huggingface.co/zjc664656505/test_repo/checkpoint-40/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ce876f2bfa6ece9e22e6dcd18e98f8c013b799e2891b866775af9a0c8f75fd7
+size 501168482

https:/huggingface.co/zjc664656505/test_repo/checkpoint-40/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b85c6b836b38386cbc056a331c448d45936679624935534eefb07af96536388e
+size 14512

https:/huggingface.co/zjc664656505/test_repo/checkpoint-40/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14a3082c01ddd710b54d2a297e71d57153e0b26ac3750b40e611c7508669a6bf
+size 14512

https:/huggingface.co/zjc664656505/test_repo/checkpoint-40/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6723962def1e1ac046512d753da0c75de4273bb8ef1e111a3f494103f9b28fdd
+size 1064

https:/huggingface.co/zjc664656505/test_repo/checkpoint-40/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

https:/huggingface.co/zjc664656505/test_repo/checkpoint-40/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

https:/huggingface.co/zjc664656505/test_repo/checkpoint-40/tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

https:/huggingface.co/zjc664656505/test_repo/checkpoint-40/trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_metric": 5.127074241638184,
+  "best_model_checkpoint": "./outputs/llama2-13B-lora-QuArch_0_1_1_alpaca_filtered-answer-context-test-new/checkpoint-4",
+  "epoch": 8.421052631578947,
+  "eval_steps": 4,
+  "global_step": 40,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21052631578947367,
+      "eval_accuracy": 0.6153846153846154,
+      "eval_loss": 5.132209300994873,
+      "eval_runtime": 14.9638,
+      "eval_samples_per_second": 3.475,
+      "eval_steps_per_second": 1.738,
+      "step": 1
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "eval_accuracy": 0.6346153846153846,
+      "eval_loss": 5.127074241638184,
+      "eval_runtime": 15.5565,
+      "eval_samples_per_second": 3.343,
+      "eval_steps_per_second": 1.671,
+      "step": 4
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "eval_accuracy": 0.6538461538461539,
+      "eval_loss": 5.060066223144531,
+      "eval_runtime": 15.7285,
+      "eval_samples_per_second": 3.306,
+      "eval_steps_per_second": 1.653,
+      "step": 8
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 2.453125,
+      "learning_rate": 2e-05,
+      "loss": 5.1323,
+      "step": 10
+    },
+    {
+      "epoch": 2.526315789473684,
+      "eval_accuracy": 0.7884615384615384,
+      "eval_loss": 4.774318695068359,
+      "eval_runtime": 15.4298,
+      "eval_samples_per_second": 3.37,
+      "eval_steps_per_second": 1.685,
+      "step": 12
+    },
+    {
+      "epoch": 3.3684210526315788,
+      "eval_accuracy": 0.9230769230769231,
+      "eval_loss": 4.04908561706543,
+      "eval_runtime": 15.16,
+      "eval_samples_per_second": 3.43,
+      "eval_steps_per_second": 1.715,
+      "step": 16
+    },
+    {
+      "epoch": 4.2105263157894735,
+      "grad_norm": 6.03125,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 4.2735,
+      "step": 20
+    },
+    {
+      "epoch": 4.2105263157894735,
+      "eval_accuracy": 0.8846153846153846,
+      "eval_loss": 2.6443593502044678,
+      "eval_runtime": 15.6094,
+      "eval_samples_per_second": 3.331,
+      "eval_steps_per_second": 1.666,
+      "step": 20
+    },
+    {
+      "epoch": 5.052631578947368,
+      "eval_accuracy": 0.9615384615384616,
+      "eval_loss": 1.0550649166107178,
+      "eval_runtime": 15.8572,
+      "eval_samples_per_second": 3.279,
+      "eval_steps_per_second": 1.64,
+      "step": 24
+    },
+    {
+      "epoch": 5.894736842105263,
+      "eval_accuracy": 0.6923076923076923,
+      "eval_loss": 0.4698377847671509,
+      "eval_runtime": 15.837,
+      "eval_samples_per_second": 3.283,
+      "eval_steps_per_second": 1.642,
+      "step": 28
+    },
+    {
+      "epoch": 6.315789473684211,
+      "grad_norm": 0.6875,
+      "learning_rate": 1.6363636363636366e-05,
+      "loss": 1.2232,
+      "step": 30
+    },
+    {
+      "epoch": 6.7368421052631575,
+      "eval_accuracy": 0.6730769230769231,
+      "eval_loss": 0.3224477767944336,
+      "eval_runtime": 15.7452,
+      "eval_samples_per_second": 3.303,
+      "eval_steps_per_second": 1.651,
+      "step": 32
+    },
+    {
+      "epoch": 7.578947368421053,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.2526957392692566,
+      "eval_runtime": 15.7721,
+      "eval_samples_per_second": 3.297,
+      "eval_steps_per_second": 1.648,
+      "step": 36
+    },
+    {
+      "epoch": 8.421052631578947,
+      "grad_norm": 0.388671875,
+      "learning_rate": 1.4545454545454546e-05,
+      "loss": 0.3083,
+      "step": 40
+    },
+    {
+      "epoch": 8.421052631578947,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.1972220242023468,
+      "eval_runtime": 15.1578,
+      "eval_samples_per_second": 3.431,
+      "eval_steps_per_second": 1.715,
+      "step": 40
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 120,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 4,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0205684108886016e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

https:/huggingface.co/zjc664656505/test_repo/checkpoint-40/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37e0924589b39a0d7454d58ec049450a3b1f1f61ba9617e2608cef4ecdefa104
+size 6072

https:/huggingface.co/zjc664656505/test_repo/checkpoint-48/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: /GenAI4HW/llama2_13b
+---
+
+# 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 0.10.0

https:/huggingface.co/zjc664656505/test_repo/checkpoint-48/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/GenAI4HW/llama2_13b",
+  "bias": "none",
+  "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_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

https:/huggingface.co/zjc664656505/test_repo/checkpoint-48/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f068d38c4c8eaf7ea36e6b17b6a7edc318a9ab16627a7aefd126f572efda0694
+size 250423448

https:/huggingface.co/zjc664656505/test_repo/checkpoint-48/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35bebe4aa4e6ab34d8755dfeea833834723c504033e7b8c6b94ba184d94ab7b0
+size 501168482

https:/huggingface.co/zjc664656505/test_repo/checkpoint-48/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:060ebfee1539c7373f021a32ddf42027530206ab1ecff4656863c52c3f89e675
+size 14512

https:/huggingface.co/zjc664656505/test_repo/checkpoint-48/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f96fd12df666349373ec766d2550474efffd2cf1ab9d868377ad24118f2fd69d
+size 14512

https:/huggingface.co/zjc664656505/test_repo/checkpoint-48/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8f46711ba1b2b4ba2d6ec118bf352d80f136b6520f019fe9bbe37d2e49f62b7
+size 1064

https:/huggingface.co/zjc664656505/test_repo/checkpoint-48/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

https:/huggingface.co/zjc664656505/test_repo/checkpoint-48/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

https:/huggingface.co/zjc664656505/test_repo/checkpoint-48/tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

https:/huggingface.co/zjc664656505/test_repo/checkpoint-48/trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_metric": 5.127074241638184,
+  "best_model_checkpoint": "./outputs/llama2-13B-lora-QuArch_0_1_1_alpaca_filtered-answer-context-test-new/checkpoint-4",
+  "epoch": 10.105263157894736,
+  "eval_steps": 4,
+  "global_step": 48,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21052631578947367,
+      "eval_accuracy": 0.6153846153846154,
+      "eval_loss": 5.132209300994873,
+      "eval_runtime": 14.9638,
+      "eval_samples_per_second": 3.475,
+      "eval_steps_per_second": 1.738,
+      "step": 1
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "eval_accuracy": 0.6346153846153846,
+      "eval_loss": 5.127074241638184,
+      "eval_runtime": 15.5565,
+      "eval_samples_per_second": 3.343,
+      "eval_steps_per_second": 1.671,
+      "step": 4
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "eval_accuracy": 0.6538461538461539,
+      "eval_loss": 5.060066223144531,
+      "eval_runtime": 15.7285,
+      "eval_samples_per_second": 3.306,
+      "eval_steps_per_second": 1.653,
+      "step": 8
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 2.453125,
+      "learning_rate": 2e-05,
+      "loss": 5.1323,
+      "step": 10
+    },
+    {
+      "epoch": 2.526315789473684,
+      "eval_accuracy": 0.7884615384615384,
+      "eval_loss": 4.774318695068359,
+      "eval_runtime": 15.4298,
+      "eval_samples_per_second": 3.37,
+      "eval_steps_per_second": 1.685,
+      "step": 12
+    },
+    {
+      "epoch": 3.3684210526315788,
+      "eval_accuracy": 0.9230769230769231,
+      "eval_loss": 4.04908561706543,
+      "eval_runtime": 15.16,
+      "eval_samples_per_second": 3.43,
+      "eval_steps_per_second": 1.715,
+      "step": 16
+    },
+    {
+      "epoch": 4.2105263157894735,
+      "grad_norm": 6.03125,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 4.2735,
+      "step": 20
+    },
+    {
+      "epoch": 4.2105263157894735,
+      "eval_accuracy": 0.8846153846153846,
+      "eval_loss": 2.6443593502044678,
+      "eval_runtime": 15.6094,
+      "eval_samples_per_second": 3.331,
+      "eval_steps_per_second": 1.666,
+      "step": 20
+    },
+    {
+      "epoch": 5.052631578947368,
+      "eval_accuracy": 0.9615384615384616,
+      "eval_loss": 1.0550649166107178,
+      "eval_runtime": 15.8572,
+      "eval_samples_per_second": 3.279,
+      "eval_steps_per_second": 1.64,
+      "step": 24
+    },
+    {
+      "epoch": 5.894736842105263,
+      "eval_accuracy": 0.6923076923076923,
+      "eval_loss": 0.4698377847671509,
+      "eval_runtime": 15.837,
+      "eval_samples_per_second": 3.283,
+      "eval_steps_per_second": 1.642,
+      "step": 28
+    },
+    {
+      "epoch": 6.315789473684211,
+      "grad_norm": 0.6875,
+      "learning_rate": 1.6363636363636366e-05,
+      "loss": 1.2232,
+      "step": 30
+    },
+    {
+      "epoch": 6.7368421052631575,
+      "eval_accuracy": 0.6730769230769231,
+      "eval_loss": 0.3224477767944336,
+      "eval_runtime": 15.7452,
+      "eval_samples_per_second": 3.303,
+      "eval_steps_per_second": 1.651,
+      "step": 32
+    },
+    {
+      "epoch": 7.578947368421053,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.2526957392692566,
+      "eval_runtime": 15.7721,
+      "eval_samples_per_second": 3.297,
+      "eval_steps_per_second": 1.648,
+      "step": 36
+    },
+    {
+      "epoch": 8.421052631578947,
+      "grad_norm": 0.388671875,
+      "learning_rate": 1.4545454545454546e-05,
+      "loss": 0.3083,
+      "step": 40
+    },
+    {
+      "epoch": 8.421052631578947,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.1972220242023468,
+      "eval_runtime": 15.1578,
+      "eval_samples_per_second": 3.431,
+      "eval_steps_per_second": 1.715,
+      "step": 40
+    },
+    {
+      "epoch": 9.263157894736842,
+      "eval_accuracy": 0.9615384615384616,
+      "eval_loss": 0.13723143935203552,
+      "eval_runtime": 16.0784,
+      "eval_samples_per_second": 3.234,
+      "eval_steps_per_second": 1.617,
+      "step": 44
+    },
+    {
+      "epoch": 10.105263157894736,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.0802871510386467,
+      "eval_runtime": 15.6064,
+      "eval_samples_per_second": 3.332,
+      "eval_steps_per_second": 1.666,
+      "step": 48
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 120,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 4,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.224682093066322e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

https:/huggingface.co/zjc664656505/test_repo/checkpoint-48/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37e0924589b39a0d7454d58ec049450a3b1f1f61ba9617e2608cef4ecdefa104
+size 6072

https:/huggingface.co/zjc664656505/test_repo/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/GenAI4HW/llama2_13b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

https:/huggingface.co/zjc664656505/test_repo/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

https:/huggingface.co/zjc664656505/test_repo/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

https:/huggingface.co/zjc664656505/test_repo/tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}