Upload folder using huggingface_hub

README.md

@@ -0,0 +1,200 @@
+---
+base_model: meta-llama/Llama-2-13b-hf
+tags:
+- generated_from_trainer
+model-index:
+- name: qlora-out
+  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)
+# qlora-out
+
+This model is a fine-tuned version of [meta-llama/Llama-2-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5302
+
+## 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: 0.0004
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 2
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.7438        | 0.01  | 20   | 0.6827          |
+| 0.8518        | 0.01  | 40   | 0.6707          |
+| 0.6798        | 0.02  | 60   | 0.6511          |
+| 0.7868        | 0.03  | 80   | 0.6231          |
+| 0.8218        | 0.04  | 100  | 0.6232          |
+| 0.6862        | 0.04  | 120  | 0.6324          |
+| 0.4989        | 0.05  | 140  | 0.6007          |
+| 0.6064        | 0.06  | 160  | 0.6127          |
+| 0.5355        | 0.06  | 180  | 0.6297          |
+| 0.6274        | 0.07  | 200  | 0.6211          |
+| 0.5512        | 0.08  | 220  | 0.6290          |
+| 0.727         | 0.08  | 240  | 0.6028          |
+| 0.5253        | 0.09  | 260  | 0.5971          |
+| 0.7679        | 0.1   | 280  | 0.5908          |
+| 0.4804        | 0.11  | 300  | 0.6154          |
+| 0.5801        | 0.11  | 320  | 0.5968          |
+| 0.3603        | 0.12  | 340  | 0.7127          |
+| 0.5948        | 0.13  | 360  | 0.5911          |
+| 0.7988        | 0.13  | 380  | 0.6060          |
+| 0.6002        | 0.14  | 400  | 0.6303          |
+| 0.5522        | 0.15  | 420  | 0.6124          |
+| 0.558         | 0.16  | 440  | 0.6061          |
+| 0.393         | 0.16  | 460  | 0.6050          |
+| 0.739         | 0.17  | 480  | 0.5977          |
+| 0.6462        | 0.18  | 500  | 0.5904          |
+| 0.5305        | 0.18  | 520  | 0.5852          |
+| 0.4749        | 0.19  | 540  | 0.5974          |
+| 0.832         | 0.2   | 560  | 0.5918          |
+| 0.7155        | 0.21  | 580  | 0.5857          |
+| 0.7374        | 0.21  | 600  | 0.6092          |
+| 1.2165        | 0.22  | 620  | 0.6071          |
+| 0.4901        | 0.23  | 640  | 0.5908          |
+| 0.4585        | 0.23  | 660  | 0.6041          |
+| 0.6474        | 0.24  | 680  | 0.5984          |
+| 0.4136        | 0.25  | 700  | 0.5860          |
+| 0.602         | 0.25  | 720  | 0.6251          |
+| 0.405         | 0.26  | 740  | 0.6182          |
+| 0.5059        | 0.27  | 760  | 0.5894          |
+| 0.4249        | 0.28  | 780  | 0.5800          |
+| 0.4847        | 0.28  | 800  | 0.5805          |
+| 0.4709        | 0.29  | 820  | 0.6140          |
+| 0.4279        | 0.3   | 840  | 0.5877          |
+| 0.7142        | 0.3   | 860  | 0.5801          |
+| 1.0536        | 0.31  | 880  | 0.6102          |
+| 0.694         | 0.32  | 900  | 0.5812          |
+| 0.5034        | 0.33  | 920  | 0.5833          |
+| 0.4208        | 0.33  | 940  | 0.5803          |
+| 0.5917        | 0.34  | 960  | 0.5756          |
+| 0.4655        | 0.35  | 980  | 0.5706          |
+| 0.4274        | 0.35  | 1000 | 0.5675          |
+| 0.3711        | 0.36  | 1020 | 0.5791          |
+| 0.6792        | 0.37  | 1040 | 0.5773          |
+| 0.3607        | 0.38  | 1060 | 0.5838          |
+| 0.5336        | 0.38  | 1080 | 0.5744          |
+| 0.5509        | 0.39  | 1100 | 0.5854          |
+| 0.2759        | 0.4   | 1120 | 0.5675          |
+| 0.5058        | 0.4   | 1140 | 0.5790          |
+| 0.4446        | 0.41  | 1160 | 0.5893          |
+| 0.4757        | 0.42  | 1180 | 0.5764          |
+| 0.4153        | 0.42  | 1200 | 0.5707          |
+| 0.5369        | 0.43  | 1220 | 0.5729          |
+| 0.4785        | 0.44  | 1240 | 0.5735          |
+| 0.4335        | 0.45  | 1260 | 0.5821          |
+| 0.5452        | 0.45  | 1280 | 0.5621          |
+| 0.3461        | 0.46  | 1300 | 0.5615          |
+| 0.5579        | 0.47  | 1320 | 0.5769          |
+| 0.6048        | 0.47  | 1340 | 0.5855          |
+| 0.6253        | 0.48  | 1360 | 0.5590          |
+| 0.5084        | 0.49  | 1380 | 0.5822          |
+| 0.3838        | 0.5   | 1400 | 0.5604          |
+| 0.667         | 0.5   | 1420 | 0.5622          |
+| 0.681         | 0.51  | 1440 | 0.5632          |
+| 0.3593        | 0.52  | 1460 | 0.5578          |
+| 0.4509        | 0.52  | 1480 | 0.5609          |
+| 0.4752        | 0.53  | 1500 | 0.5494          |
+| 0.3152        | 0.54  | 1520 | 0.5541          |
+| 0.3699        | 0.55  | 1540 | 0.5449          |
+| 0.3009        | 0.55  | 1560 | 0.5656          |
+| 0.2867        | 0.56  | 1580 | 0.5499          |
+| 0.7261        | 0.57  | 1600 | 0.5490          |
+| 0.5149        | 0.57  | 1620 | 0.5565          |
+| 0.473         | 0.58  | 1640 | 0.5445          |
+| 0.9732        | 0.59  | 1660 | 0.5505          |
+| 0.9606        | 0.59  | 1680 | 0.5471          |
+| 0.2714        | 0.6   | 1700 | 0.5651          |
+| 0.4927        | 0.61  | 1720 | 0.5527          |
+| 0.6928        | 0.62  | 1740 | 0.5433          |
+| 0.3776        | 0.62  | 1760 | 0.5507          |
+| 0.4636        | 0.63  | 1780 | 0.5443          |
+| 0.43          | 0.64  | 1800 | 0.5527          |
+| 0.5656        | 0.64  | 1820 | 0.5478          |
+| 0.729         | 0.65  | 1840 | 0.5542          |
+| 0.4355        | 0.66  | 1860 | 0.5411          |
+| 0.377         | 0.67  | 1880 | 0.5426          |
+| 0.5345        | 0.67  | 1900 | 0.5434          |
+| 0.4042        | 0.68  | 1920 | 0.5383          |
+| 0.3676        | 0.69  | 1940 | 0.5372          |
+| 0.4758        | 0.69  | 1960 | 0.5411          |
+| 0.4919        | 0.7   | 1980 | 0.5353          |
+| 0.2312        | 0.71  | 2000 | 0.5351          |
+| 0.7224        | 0.71  | 2020 | 0.5364          |
+| 0.3617        | 0.72  | 2040 | 0.5357          |
+| 0.8601        | 0.73  | 2060 | 0.5402          |
+| 0.3218        | 0.74  | 2080 | 0.5309          |
+| 0.3611        | 0.74  | 2100 | 0.5412          |
+| 0.4466        | 0.75  | 2120 | 0.5432          |
+| 0.5551        | 0.76  | 2140 | 0.5345          |
+| 0.4047        | 0.76  | 2160 | 0.5321          |
+| 0.4624        | 0.77  | 2180 | 0.5357          |
+| 0.5704        | 0.78  | 2200 | 0.5325          |
+| 0.715         | 0.79  | 2220 | 0.5313          |
+| 0.4913        | 0.79  | 2240 | 0.5300          |
+| 0.3605        | 0.8   | 2260 | 0.5294          |
+| 0.234         | 0.81  | 2280 | 0.5318          |
+| 0.6128        | 0.81  | 2300 | 0.5365          |
+| 0.236         | 0.82  | 2320 | 0.5342          |
+| 0.3503        | 0.83  | 2340 | 0.5348          |
+| 0.4874        | 0.84  | 2360 | 0.5313          |
+| 0.5999        | 0.84  | 2380 | 0.5312          |
+| 0.2757        | 0.85  | 2400 | 0.5292          |
+| 0.322         | 0.86  | 2420 | 0.5299          |
+| 0.4368        | 0.86  | 2440 | 0.5318          |
+| 0.318         | 0.87  | 2460 | 0.5319          |
+| 0.7192        | 0.88  | 2480 | 0.5307          |
+| 0.3465        | 0.88  | 2500 | 0.5315          |
+| 0.4098        | 0.89  | 2520 | 0.5312          |
+| 0.682         | 0.9   | 2540 | 0.5308          |
+| 1.4551        | 0.91  | 2560 | 0.5310          |
+| 0.4396        | 0.91  | 2580 | 0.5301          |
+| 0.5932        | 0.92  | 2600 | 0.5298          |
+| 0.3978        | 0.93  | 2620 | 0.5292          |
+| 0.2823        | 0.93  | 2640 | 0.5296          |
+| 0.4293        | 0.94  | 2660 | 0.5294          |
+| 0.4646        | 0.95  | 2680 | 0.5296          |
+| 0.8203        | 0.96  | 2700 | 0.5295          |
+| 0.351         | 0.96  | 2720 | 0.5299          |
+| 0.328         | 0.97  | 2740 | 0.5292          |
+| 0.3347        | 0.98  | 2760 | 0.5302          |
+| 0.2608        | 0.98  | 2780 | 0.5296          |
+| 0.4274        | 0.99  | 2800 | 0.5294          |
+| 0.3349        | 1.0   | 2820 | 0.5302          |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-13b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98acb83d328e6c47c3e44b8fe7504fc2aced6a4a7e466854420e280d93bd3a17
+size 250549581

checkpoint-2825/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: meta-llama/Llama-2-13b-hf
+---
+
+# 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]
+- **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 Data 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 Data 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0

checkpoint-2825/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-13b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-2825/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98acb83d328e6c47c3e44b8fe7504fc2aced6a4a7e466854420e280d93bd3a17
+size 250549581

checkpoint-2825/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a4cd55c635ec6885df0e0001b122b7bbc32a1c0eabe4856b07fa732f5366cd5
+size 501031421

checkpoint-2825/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8467903f35780044ed8019a49536b3688df86da6f4bf2f7776da1d752c8be2f1
+size 14575

checkpoint-2825/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3969006733e1a504cb51bc523adf75b09c949dbd9b94e70ba413bd1aa12d9923
+size 627

checkpoint-2825/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85483b8b3996819c2086e17ee67ebdc7e6e3e231642e48fcc2c02e328cfd1464
+size 4475

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-13b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

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
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}