Upload folder using huggingface_hub

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+base_model: teknium/OpenHermes-2.5-Mistral-7B
+tags:
+- generated_from_trainer
+model-index:
+- name: lora-outB
+  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)
+# lora-outB
+
+This model is a fine-tuned version of [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4546
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 5
+- total_train_batch_size: 40
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.5629        | 0.75  | 25   | 1.6511          |
+| 1.5253        | 1.5   | 50   | 1.5730          |
+| 1.3363        | 2.25  | 75   | 1.5014          |
+| 1.4017        | 2.99  | 100  | 1.4690          |
+| 1.2677        | 3.74  | 125  | 1.4593          |
+| 1.351         | 4.49  | 150  | 1.4546          |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.1.0+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": "teknium/OpenHermes-2.5-Mistral-7B",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cc4f98f72e6ab33b93346265f31f32adcc362ffd925e5c929c2561d2fb3dd34
+size 1342339274

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

checkpoint-100/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: teknium/OpenHermes-2.5-Mistral-7B
+---
+
+# 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: True
+- load_in_4bit: False
+- 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: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+### Framework versions
+
+
+- PEFT 0.6.0

checkpoint-100/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "teknium/OpenHermes-2.5-Mistral-7B",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-100/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17456f76fd7f3e462cafac25cfea3e25b950daa3039e42090bce88b5cd477666
+size 1342339274

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9181035a5616518d113eaec2ff777dc792db8076fb052494f25f8a486552c08f
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5d2ad6e302cd5816cfcc3c90378a6581d35b9b572941ccc3a9cc7f9abac53f2
+size 1064

checkpoint-100/trainer_state.json

@@ -0,0 +1,651 @@
+{
+  "best_metric": 1.4689786434173584,
+  "best_model_checkpoint": "./lora-outB/checkpoint-100",
+  "epoch": 2.9940119760479043,
+  "eval_steps": 25,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.866,
+      "step": 1
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.7383,
+      "step": 2
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 6e-06,
+      "loss": 1.8306,
+      "step": 3
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.9213,
+      "step": 4
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1e-05,
+      "loss": 1.9524,
+      "step": 5
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.2e-05,
+      "loss": 1.7308,
+      "step": 6
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.4e-05,
+      "loss": 1.7334,
+      "step": 7
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.6749,
+      "step": 8
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.8e-05,
+      "loss": 1.805,
+      "step": 9
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2e-05,
+      "loss": 1.778,
+      "step": 10
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9997946042345128e-05,
+      "loss": 1.7804,
+      "step": 11
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9991785013128922e-05,
+      "loss": 1.8191,
+      "step": 12
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.998151944325001e-05,
+      "loss": 1.7089,
+      "step": 13
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.996715354971755e-05,
+      "loss": 1.7131,
+      "step": 14
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.994869323391895e-05,
+      "loss": 1.917,
+      "step": 15
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9926146079195597e-05,
+      "loss": 1.6701,
+      "step": 16
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.989952134772769e-05,
+      "loss": 1.7119,
+      "step": 17
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.9868829976729444e-05,
+      "loss": 1.7037,
+      "step": 18
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.983408457395613e-05,
+      "loss": 1.7314,
+      "step": 19
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.9795299412524948e-05,
+      "loss": 1.6771,
+      "step": 20
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.975249042505174e-05,
+      "loss": 1.6734,
+      "step": 21
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.970567519710602e-05,
+      "loss": 1.689,
+      "step": 22
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.9654872959986936e-05,
+      "loss": 1.7452,
+      "step": 23
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.960010458282326e-05,
+      "loss": 1.7126,
+      "step": 24
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.954139256400049e-05,
+      "loss": 1.5629,
+      "step": 25
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 1.6511253118515015,
+      "eval_runtime": 5.4427,
+      "eval_samples_per_second": 5.145,
+      "eval_steps_per_second": 0.735,
+      "step": 25
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.947876102191873e-05,
+      "loss": 1.6948,
+      "step": 26
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.9412235685085034e-05,
+      "loss": 1.5969,
+      "step": 27
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.9341843881544372e-05,
+      "loss": 1.5367,
+      "step": 28
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.926761452765349e-05,
+      "loss": 1.463,
+      "step": 29
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.918957811620231e-05,
+      "loss": 1.4575,
+      "step": 30
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.9107766703887764e-05,
+      "loss": 1.5928,
+      "step": 31
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.9022213898145176e-05,
+      "loss": 1.5604,
+      "step": 32
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.893295484334259e-05,
+      "loss": 1.6508,
+      "step": 33
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.8840026206343786e-05,
+      "loss": 1.4583,
+      "step": 34
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.8743466161445823e-05,
+      "loss": 1.7124,
+      "step": 35
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.8643314374697377e-05,
+      "loss": 1.462,
+      "step": 36
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.853961198760426e-05,
+      "loss": 1.6664,
+      "step": 37
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.8432401600228823e-05,
+      "loss": 1.6264,
+      "step": 38
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.832172725369024e-05,
+      "loss": 1.6704,
+      "step": 39
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.8207634412072765e-05,
+      "loss": 1.5221,
+      "step": 40
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 1.5411,
+      "step": 41
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.7969382102129153e-05,
+      "loss": 1.4493,
+      "step": 42
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.7845320505834176e-05,
+      "loss": 1.4783,
+      "step": 43
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.771803611831762e-05,
+      "loss": 1.5882,
+      "step": 44
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.758758122692791e-05,
+      "loss": 1.5848,
+      "step": 45
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.74540094214296e-05,
+      "loss": 1.4439,
+      "step": 46
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.7317375571989158e-05,
+      "loss": 1.5398,
+      "step": 47
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.717773580663479e-05,
+      "loss": 1.3689,
+      "step": 48
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.703514748819948e-05,
+      "loss": 1.5311,
+      "step": 49
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.688966919075687e-05,
+      "loss": 1.5253,
+      "step": 50
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 1.5729879140853882,
+      "eval_runtime": 5.4053,
+      "eval_samples_per_second": 5.18,
+      "eval_steps_per_second": 0.74,
+      "step": 50
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.6741360675559475e-05,
+      "loss": 1.3689,
+      "step": 51
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1.659028286648932e-05,
+      "loss": 1.4167,
+      "step": 52
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1.6436497825030886e-05,
+      "loss": 1.6581,
+      "step": 53
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.6280068724776795e-05,
+      "loss": 1.5004,
+      "step": 54
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.612105982547663e-05,
+      "loss": 1.4912,
+      "step": 55
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.5959536446639572e-05,
+      "loss": 1.5128,
+      "step": 56
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.57955649407017e-05,
+      "loss": 1.4908,
+      "step": 57
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 1.562921266576898e-05,
+      "loss": 1.4826,
+      "step": 58
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.5460547957947105e-05,
+      "loss": 1.423,
+      "step": 59
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.5289640103269626e-05,
+      "loss": 1.5394,
+      "step": 60
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.5116559309235825e-05,
+      "loss": 1.4102,
+      "step": 61
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.4941376675970058e-05,
+      "loss": 1.3556,
+      "step": 62
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.4764164167014451e-05,
+      "loss": 1.5444,
+      "step": 63
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.4584994579766865e-05,
+      "loss": 1.4466,
+      "step": 64
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.4403941515576344e-05,
+      "loss": 1.4467,
+      "step": 65
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.422107934950832e-05,
+      "loss": 1.4268,
+      "step": 66
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 1.4036483199791949e-05,
+      "loss": 1.4073,
+      "step": 67
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.3850228896962178e-05,
+      "loss": 1.5186,
+      "step": 68
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 1.366239295270923e-05,
+      "loss": 1.5014,
+      "step": 69
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1.3473052528448203e-05,
+      "loss": 1.3933,
+      "step": 70
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 1.3282285403621864e-05,
+      "loss": 1.4067,
+      "step": 71
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 1.5052,
+      "step": 72
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 1.2896785068234925e-05,
+      "loss": 1.3016,
+      "step": 73
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 1.2702210217947289e-05,
+      "loss": 1.3951,
+      "step": 74
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 1.2506525322587207e-05,
+      "loss": 1.3363,
+      "step": 75
+    },
+    {
+      "epoch": 2.25,
+      "eval_loss": 1.5013550519943237,
+      "eval_runtime": 5.4016,
+      "eval_samples_per_second": 5.184,
+      "eval_steps_per_second": 0.741,
+      "step": 75
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 1.2309810767852435e-05,
+      "loss": 1.3622,
+      "step": 76
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 1.2112147362416076e-05,
+      "loss": 1.3339,
+      "step": 77
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.1913616304731064e-05,
+      "loss": 1.3832,
+      "step": 78
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 1.1714299149674538e-05,
+      "loss": 1.2172,
+      "step": 79
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.1514277775045768e-05,
+      "loss": 1.2421,
+      "step": 80
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.1313634347931466e-05,
+      "loss": 1.3649,
+      "step": 81
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.1112451290952238e-05,
+      "loss": 1.5337,
+      "step": 82
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.0910811248404064e-05,
+      "loss": 1.2464,
+      "step": 83
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.070879705230873e-05,
+      "loss": 1.4806,
+      "step": 84
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.0506491688387128e-05,
+      "loss": 1.3603,
+      "step": 85
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.030397826196943e-05,
+      "loss": 1.2416,
+      "step": 86
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 1.0101339963856112e-05,
+      "loss": 1.2974,
+      "step": 87
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 9.898660036143893e-06,
+      "loss": 1.6356,
+      "step": 88
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 9.696021738030575e-06,
+      "loss": 1.2952,
+      "step": 89
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 9.493508311612874e-06,
+      "loss": 1.3857,
+      "step": 90
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 9.291202947691272e-06,
+      "loss": 1.3712,
+      "step": 91
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 9.089188751595937e-06,
+      "loss": 1.3713,
+      "step": 92
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 8.887548709047765e-06,
+      "loss": 1.4597,
+      "step": 93
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 8.686365652068536e-06,
+      "loss": 1.225,
+      "step": 94
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 8.485722224954237e-06,
+      "loss": 1.3307,
+      "step": 95
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 8.285700850325467e-06,
+      "loss": 1.3423,
+      "step": 96
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 8.086383695268937e-06,
+      "loss": 1.352,
+      "step": 97
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 7.887852637583927e-06,
+      "loss": 1.3908,
+      "step": 98
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 7.690189232147566e-06,
+      "loss": 1.406,
+      "step": 99
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 7.493474677412795e-06,
+      "loss": 1.4017,
+      "step": 100
+    },
+    {
+      "epoch": 2.99,
+      "eval_loss": 1.4689786434173584,
+      "eval_runtime": 5.4385,
+      "eval_samples_per_second": 5.148,
+      "eval_steps_per_second": 0.735,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 165,
+  "num_train_epochs": 5,
+  "save_steps": 50,
+  "total_flos": 1.1345883505360896e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:218e6b2697498e27486ba1b06651dcc4e8143ab7c7f81e54381850c57f692daf
+size 4920

checkpoint-150/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: teknium/OpenHermes-2.5-Mistral-7B
+---
+
+# 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: True
+- load_in_4bit: False
+- 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: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+### Framework versions
+
+
+- PEFT 0.6.0

checkpoint-150/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "teknium/OpenHermes-2.5-Mistral-7B",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-150/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cc4f98f72e6ab33b93346265f31f32adcc362ffd925e5c929c2561d2fb3dd34
+size 1342339274

checkpoint-150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4be8ffc6a9fea3b3284aed54a6b2d8a63e87d3db1ad09cac5db71797b5aab76
+size 2684631802

checkpoint-150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a527cb0c734c3ed4b752b8c8297514a163a179a2ae48f49423d896146d405ad9
+size 14244

checkpoint-150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cc87633ee72247fca3b2919660e92d8e30dcf0e412f83ccd1f650d1d2f8e39c
+size 1064

checkpoint-150/trainer_state.json

@@ -0,0 +1,967 @@
+{
+  "best_metric": 1.4545527696609497,
+  "best_model_checkpoint": "./lora-outB/checkpoint-150",
+  "epoch": 4.491017964071856,
+  "eval_steps": 25,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.866,
+      "step": 1
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.7383,
+      "step": 2
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 6e-06,
+      "loss": 1.8306,
+      "step": 3
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.9213,
+      "step": 4
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1e-05,
+      "loss": 1.9524,
+      "step": 5
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.2e-05,
+      "loss": 1.7308,
+      "step": 6
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.4e-05,
+      "loss": 1.7334,
+      "step": 7
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.6749,
+      "step": 8
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.8e-05,
+      "loss": 1.805,
+      "step": 9
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2e-05,
+      "loss": 1.778,
+      "step": 10
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9997946042345128e-05,
+      "loss": 1.7804,
+      "step": 11
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9991785013128922e-05,
+      "loss": 1.8191,
+      "step": 12
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.998151944325001e-05,
+      "loss": 1.7089,
+      "step": 13
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.996715354971755e-05,
+      "loss": 1.7131,
+      "step": 14
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.994869323391895e-05,
+      "loss": 1.917,
+      "step": 15
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9926146079195597e-05,
+      "loss": 1.6701,
+      "step": 16
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.989952134772769e-05,
+      "loss": 1.7119,
+      "step": 17
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.9868829976729444e-05,
+      "loss": 1.7037,
+      "step": 18
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.983408457395613e-05,
+      "loss": 1.7314,
+      "step": 19
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.9795299412524948e-05,
+      "loss": 1.6771,
+      "step": 20
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.975249042505174e-05,
+      "loss": 1.6734,
+      "step": 21
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.970567519710602e-05,
+      "loss": 1.689,
+      "step": 22
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.9654872959986936e-05,
+      "loss": 1.7452,
+      "step": 23
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.960010458282326e-05,
+      "loss": 1.7126,
+      "step": 24
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.954139256400049e-05,
+      "loss": 1.5629,
+      "step": 25
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 1.6511253118515015,
+      "eval_runtime": 5.4427,
+      "eval_samples_per_second": 5.145,
+      "eval_steps_per_second": 0.735,
+      "step": 25
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.947876102191873e-05,
+      "loss": 1.6948,
+      "step": 26
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.9412235685085034e-05,
+      "loss": 1.5969,
+      "step": 27
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.9341843881544372e-05,
+      "loss": 1.5367,
+      "step": 28
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.926761452765349e-05,
+      "loss": 1.463,
+      "step": 29
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.918957811620231e-05,
+      "loss": 1.4575,
+      "step": 30
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.9107766703887764e-05,
+      "loss": 1.5928,
+      "step": 31
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.9022213898145176e-05,
+      "loss": 1.5604,
+      "step": 32
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.893295484334259e-05,
+      "loss": 1.6508,
+      "step": 33
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.8840026206343786e-05,
+      "loss": 1.4583,
+      "step": 34
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.8743466161445823e-05,
+      "loss": 1.7124,
+      "step": 35
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.8643314374697377e-05,
+      "loss": 1.462,
+      "step": 36
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.853961198760426e-05,
+      "loss": 1.6664,
+      "step": 37
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.8432401600228823e-05,
+      "loss": 1.6264,
+      "step": 38
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.832172725369024e-05,
+      "loss": 1.6704,
+      "step": 39
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.8207634412072765e-05,
+      "loss": 1.5221,
+      "step": 40
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 1.5411,
+      "step": 41
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.7969382102129153e-05,
+      "loss": 1.4493,
+      "step": 42
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.7845320505834176e-05,
+      "loss": 1.4783,
+      "step": 43
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.771803611831762e-05,
+      "loss": 1.5882,
+      "step": 44
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.758758122692791e-05,
+      "loss": 1.5848,
+      "step": 45
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.74540094214296e-05,
+      "loss": 1.4439,
+      "step": 46
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.7317375571989158e-05,
+      "loss": 1.5398,
+      "step": 47
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.717773580663479e-05,
+      "loss": 1.3689,
+      "step": 48
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.703514748819948e-05,
+      "loss": 1.5311,
+      "step": 49
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.688966919075687e-05,
+      "loss": 1.5253,
+      "step": 50
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 1.5729879140853882,
+      "eval_runtime": 5.4053,
+      "eval_samples_per_second": 5.18,
+      "eval_steps_per_second": 0.74,
+      "step": 50
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.6741360675559475e-05,
+      "loss": 1.3689,
+      "step": 51
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1.659028286648932e-05,
+      "loss": 1.4167,
+      "step": 52
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1.6436497825030886e-05,
+      "loss": 1.6581,
+      "step": 53
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.6280068724776795e-05,
+      "loss": 1.5004,
+      "step": 54
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.612105982547663e-05,
+      "loss": 1.4912,
+      "step": 55
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.5959536446639572e-05,
+      "loss": 1.5128,
+      "step": 56
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.57955649407017e-05,
+      "loss": 1.4908,
+      "step": 57
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 1.562921266576898e-05,
+      "loss": 1.4826,
+      "step": 58
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.5460547957947105e-05,
+      "loss": 1.423,
+      "step": 59
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.5289640103269626e-05,
+      "loss": 1.5394,
+      "step": 60
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.5116559309235825e-05,
+      "loss": 1.4102,
+      "step": 61
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.4941376675970058e-05,
+      "loss": 1.3556,
+      "step": 62
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.4764164167014451e-05,
+      "loss": 1.5444,
+      "step": 63
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.4584994579766865e-05,
+      "loss": 1.4466,
+      "step": 64
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.4403941515576344e-05,
+      "loss": 1.4467,
+      "step": 65
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.422107934950832e-05,
+      "loss": 1.4268,
+      "step": 66
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 1.4036483199791949e-05,
+      "loss": 1.4073,
+      "step": 67
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.3850228896962178e-05,
+      "loss": 1.5186,
+      "step": 68
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 1.366239295270923e-05,
+      "loss": 1.5014,
+      "step": 69
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1.3473052528448203e-05,
+      "loss": 1.3933,
+      "step": 70
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 1.3282285403621864e-05,
+      "loss": 1.4067,
+      "step": 71
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 1.5052,
+      "step": 72
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 1.2896785068234925e-05,
+      "loss": 1.3016,
+      "step": 73
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 1.2702210217947289e-05,
+      "loss": 1.3951,
+      "step": 74
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 1.2506525322587207e-05,
+      "loss": 1.3363,
+      "step": 75
+    },
+    {
+      "epoch": 2.25,
+      "eval_loss": 1.5013550519943237,
+      "eval_runtime": 5.4016,
+      "eval_samples_per_second": 5.184,
+      "eval_steps_per_second": 0.741,
+      "step": 75
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 1.2309810767852435e-05,
+      "loss": 1.3622,
+      "step": 76
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 1.2112147362416076e-05,
+      "loss": 1.3339,
+      "step": 77
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.1913616304731064e-05,
+      "loss": 1.3832,
+      "step": 78
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 1.1714299149674538e-05,
+      "loss": 1.2172,
+      "step": 79
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.1514277775045768e-05,
+      "loss": 1.2421,
+      "step": 80
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.1313634347931466e-05,
+      "loss": 1.3649,
+      "step": 81
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.1112451290952238e-05,
+      "loss": 1.5337,
+      "step": 82
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.0910811248404064e-05,
+      "loss": 1.2464,
+      "step": 83
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.070879705230873e-05,
+      "loss": 1.4806,
+      "step": 84
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.0506491688387128e-05,
+      "loss": 1.3603,
+      "step": 85
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.030397826196943e-05,
+      "loss": 1.2416,
+      "step": 86
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 1.0101339963856112e-05,
+      "loss": 1.2974,
+      "step": 87
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 9.898660036143893e-06,
+      "loss": 1.6356,
+      "step": 88
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 9.696021738030575e-06,
+      "loss": 1.2952,
+      "step": 89
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 9.493508311612874e-06,
+      "loss": 1.3857,
+      "step": 90
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 9.291202947691272e-06,
+      "loss": 1.3712,
+      "step": 91
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 9.089188751595937e-06,
+      "loss": 1.3713,
+      "step": 92
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 8.887548709047765e-06,
+      "loss": 1.4597,
+      "step": 93
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 8.686365652068536e-06,
+      "loss": 1.225,
+      "step": 94
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 8.485722224954237e-06,
+      "loss": 1.3307,
+      "step": 95
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 8.285700850325467e-06,
+      "loss": 1.3423,
+      "step": 96
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 8.086383695268937e-06,
+      "loss": 1.352,
+      "step": 97
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 7.887852637583927e-06,
+      "loss": 1.3908,
+      "step": 98
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 7.690189232147566e-06,
+      "loss": 1.406,
+      "step": 99
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 7.493474677412795e-06,
+      "loss": 1.4017,
+      "step": 100
+    },
+    {
+      "epoch": 2.99,
+      "eval_loss": 1.4689786434173584,
+      "eval_runtime": 5.4385,
+      "eval_samples_per_second": 5.148,
+      "eval_steps_per_second": 0.735,
+      "step": 100
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 7.297789782052716e-06,
+      "loss": 1.2587,
+      "step": 101
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 7.10321493176508e-06,
+      "loss": 1.2309,
+      "step": 102
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 1.3232,
+      "step": 103
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 6.717714596378138e-06,
+      "loss": 1.2715,
+      "step": 104
+    },
+    {
+      "epoch": 3.14,
+      "learning_rate": 6.526947471551799e-06,
+      "loss": 1.3015,
+      "step": 105
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 6.337607047290774e-06,
+      "loss": 1.3752,
+      "step": 106
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 6.149771103037821e-06,
+      "loss": 1.3156,
+      "step": 107
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 5.963516800208056e-06,
+      "loss": 1.3419,
+      "step": 108
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 5.7789206504916815e-06,
+      "loss": 1.4729,
+      "step": 109
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 5.5960584844236565e-06,
+      "loss": 1.3619,
+      "step": 110
+    },
+    {
+      "epoch": 3.32,
+      "learning_rate": 5.415005420233141e-06,
+      "loss": 1.4708,
+      "step": 111
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 5.235835832985552e-06,
+      "loss": 1.4684,
+      "step": 112
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 5.058623324029944e-06,
+      "loss": 1.2379,
+      "step": 113
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 4.8834406907641784e-06,
+      "loss": 1.2921,
+      "step": 114
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 4.710359896730379e-06,
+      "loss": 1.3846,
+      "step": 115
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 4.539452042052901e-06,
+      "loss": 1.218,
+      "step": 116
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 4.370787334231026e-06,
+      "loss": 1.2349,
+      "step": 117
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 4.204435059298303e-06,
+      "loss": 1.1808,
+      "step": 118
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 4.040463553360431e-06,
+      "loss": 1.2824,
+      "step": 119
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 3.878940174523371e-06,
+      "loss": 1.4456,
+      "step": 120
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 3.7199312752232053e-06,
+      "loss": 1.3098,
+      "step": 121
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 3.563502174969117e-06,
+      "loss": 1.2517,
+      "step": 122
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 3.409717133510683e-06,
+      "loss": 1.3281,
+      "step": 123
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 3.258639324440527e-06,
+      "loss": 1.3068,
+      "step": 124
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 3.110330809243134e-06,
+      "loss": 1.2677,
+      "step": 125
+    },
+    {
+      "epoch": 3.74,
+      "eval_loss": 1.4592927694320679,
+      "eval_runtime": 5.3759,
+      "eval_samples_per_second": 5.208,
+      "eval_steps_per_second": 0.744,
+      "step": 125
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 2.964852511800519e-06,
+      "loss": 1.2642,
+      "step": 126
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 2.822264193365212e-06,
+      "loss": 1.2629,
+      "step": 127
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 2.6826244280108438e-06,
+      "loss": 1.4554,
+      "step": 128
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 2.545990578570404e-06,
+      "loss": 1.4209,
+      "step": 129
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 2.4124187730720916e-06,
+      "loss": 1.3152,
+      "step": 130
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 2.2819638816823796e-06,
+      "loss": 1.2729,
+      "step": 131
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 2.154679494165829e-06,
+      "loss": 1.3608,
+      "step": 132
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 2.030617897870851e-06,
+      "loss": 1.3871,
+      "step": 133
+    },
+    {
+      "epoch": 4.01,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 1.3255,
+      "step": 134
+    },
+    {
+      "epoch": 4.04,
+      "learning_rate": 1.7923655879272395e-06,
+      "loss": 1.3443,
+      "step": 135
+    },
+    {
+      "epoch": 4.07,
+      "learning_rate": 1.6782727463097626e-06,
+      "loss": 1.41,
+      "step": 136
+    },
+    {
+      "epoch": 4.1,
+      "learning_rate": 1.5675983997711797e-06,
+      "loss": 1.2783,
+      "step": 137
+    },
+    {
+      "epoch": 4.13,
+      "learning_rate": 1.4603880123957448e-06,
+      "loss": 1.169,
+      "step": 138
+    },
+    {
+      "epoch": 4.16,
+      "learning_rate": 1.356685625302625e-06,
+      "loss": 1.1928,
+      "step": 139
+    },
+    {
+      "epoch": 4.19,
+      "learning_rate": 1.2565338385541792e-06,
+      "loss": 1.4349,
+      "step": 140
+    },
+    {
+      "epoch": 4.22,
+      "learning_rate": 1.159973793656215e-06,
+      "loss": 1.4173,
+      "step": 141
+    },
+    {
+      "epoch": 4.25,
+      "learning_rate": 1.0670451566574102e-06,
+      "loss": 1.3533,
+      "step": 142
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 9.77786101854825e-07,
+      "loss": 1.188,
+      "step": 143
+    },
+    {
+      "epoch": 4.31,
+      "learning_rate": 8.92233296112236e-07,
+      "loss": 1.2933,
+      "step": 144
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 8.10421883797694e-07,
+      "loss": 1.2848,
+      "step": 145
+    },
+    {
+      "epoch": 4.37,
+      "learning_rate": 7.32385472346514e-07,
+      "loss": 1.3775,
+      "step": 146
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 6.581561184556296e-07,
+      "loss": 1.2679,
+      "step": 147
+    },
+    {
+      "epoch": 4.43,
+      "learning_rate": 5.877643149149669e-07,
+      "loss": 1.2643,
+      "step": 148
+    },
+    {
+      "epoch": 4.46,
+      "learning_rate": 5.212389780812733e-07,
+      "loss": 1.3166,
+      "step": 149
+    },
+    {
+      "epoch": 4.49,
+      "learning_rate": 4.5860743599951186e-07,
+      "loss": 1.351,
+      "step": 150
+    },
+    {
+      "epoch": 4.49,
+      "eval_loss": 1.4545527696609497,
+      "eval_runtime": 5.4009,
+      "eval_samples_per_second": 5.184,
+      "eval_steps_per_second": 0.741,
+      "step": 150
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 165,
+  "num_train_epochs": 5,
+  "save_steps": 50,
+  "total_flos": 1.7018825258041344e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:218e6b2697498e27486ba1b06651dcc4e8143ab7c7f81e54381850c57f692daf
+size 4920

checkpoint-50/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: teknium/OpenHermes-2.5-Mistral-7B
+---
+
+# 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: True
+- load_in_4bit: False
+- 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: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+### Framework versions
+
+
+- PEFT 0.6.0

checkpoint-50/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "teknium/OpenHermes-2.5-Mistral-7B",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-50/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a3cc46d7df08a29e40f60cbaebba3ffd740879f78150efafa78f8c933c9e6f0
+size 1342339274

checkpoint-50/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b672f6b7accac26d4e8ea17b64b36cda058493ceafae493ea42869a72891a8df
+size 14244

checkpoint-50/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66fc4977d94a5c5aba2bc63e71c04c1edca2632bc98631eb22dde6d4b9c38dbf
+size 1064

checkpoint-50/trainer_state.json

@@ -0,0 +1,335 @@
+{
+  "best_metric": 1.5729879140853882,
+  "best_model_checkpoint": "./lora-outB/checkpoint-50",
+  "epoch": 1.4970059880239521,
+  "eval_steps": 25,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.866,
+      "step": 1
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.7383,
+      "step": 2
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 6e-06,
+      "loss": 1.8306,
+      "step": 3
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.9213,
+      "step": 4
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1e-05,
+      "loss": 1.9524,
+      "step": 5
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.2e-05,
+      "loss": 1.7308,
+      "step": 6
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.4e-05,
+      "loss": 1.7334,
+      "step": 7
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.6749,
+      "step": 8
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.8e-05,
+      "loss": 1.805,
+      "step": 9
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2e-05,
+      "loss": 1.778,
+      "step": 10
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9997946042345128e-05,
+      "loss": 1.7804,
+      "step": 11
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9991785013128922e-05,
+      "loss": 1.8191,
+      "step": 12
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.998151944325001e-05,
+      "loss": 1.7089,
+      "step": 13
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.996715354971755e-05,
+      "loss": 1.7131,
+      "step": 14
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.994869323391895e-05,
+      "loss": 1.917,
+      "step": 15
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9926146079195597e-05,
+      "loss": 1.6701,
+      "step": 16
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.989952134772769e-05,
+      "loss": 1.7119,
+      "step": 17
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.9868829976729444e-05,
+      "loss": 1.7037,
+      "step": 18
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.983408457395613e-05,
+      "loss": 1.7314,
+      "step": 19
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.9795299412524948e-05,
+      "loss": 1.6771,
+      "step": 20
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.975249042505174e-05,
+      "loss": 1.6734,
+      "step": 21
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.970567519710602e-05,
+      "loss": 1.689,
+      "step": 22
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.9654872959986936e-05,
+      "loss": 1.7452,
+      "step": 23
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.960010458282326e-05,
+      "loss": 1.7126,
+      "step": 24
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.954139256400049e-05,
+      "loss": 1.5629,
+      "step": 25
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 1.6511253118515015,
+      "eval_runtime": 5.4427,
+      "eval_samples_per_second": 5.145,
+      "eval_steps_per_second": 0.735,
+      "step": 25
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.947876102191873e-05,
+      "loss": 1.6948,
+      "step": 26
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.9412235685085034e-05,
+      "loss": 1.5969,
+      "step": 27
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.9341843881544372e-05,
+      "loss": 1.5367,
+      "step": 28
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.926761452765349e-05,
+      "loss": 1.463,
+      "step": 29
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.918957811620231e-05,
+      "loss": 1.4575,
+      "step": 30
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.9107766703887764e-05,
+      "loss": 1.5928,
+      "step": 31
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.9022213898145176e-05,
+      "loss": 1.5604,
+      "step": 32
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.893295484334259e-05,
+      "loss": 1.6508,
+      "step": 33
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.8840026206343786e-05,
+      "loss": 1.4583,
+      "step": 34
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.8743466161445823e-05,
+      "loss": 1.7124,
+      "step": 35
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.8643314374697377e-05,
+      "loss": 1.462,
+      "step": 36
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.853961198760426e-05,
+      "loss": 1.6664,
+      "step": 37
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.8432401600228823e-05,
+      "loss": 1.6264,
+      "step": 38
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.832172725369024e-05,
+      "loss": 1.6704,
+      "step": 39
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.8207634412072765e-05,
+      "loss": 1.5221,
+      "step": 40
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 1.5411,
+      "step": 41
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.7969382102129153e-05,
+      "loss": 1.4493,
+      "step": 42
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.7845320505834176e-05,
+      "loss": 1.4783,
+      "step": 43
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.771803611831762e-05,
+      "loss": 1.5882,
+      "step": 44
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.758758122692791e-05,
+      "loss": 1.5848,
+      "step": 45
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.74540094214296e-05,
+      "loss": 1.4439,
+      "step": 46
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.7317375571989158e-05,
+      "loss": 1.5398,
+      "step": 47
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.717773580663479e-05,
+      "loss": 1.3689,
+      "step": 48
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.703514748819948e-05,
+      "loss": 1.5311,
+      "step": 49
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.688966919075687e-05,
+      "loss": 1.5253,
+      "step": 50
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 1.5729879140853882,
+      "eval_runtime": 5.4053,
+      "eval_samples_per_second": 5.18,
+      "eval_steps_per_second": 0.74,
+      "step": 50
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 165,
+  "num_train_epochs": 5,
+  "save_steps": 50,
+  "total_flos": 5.618042316364186e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-50/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:218e6b2697498e27486ba1b06651dcc4e8143ab7c7f81e54381850c57f692daf
+size 4920

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "teknium/OpenHermes-2.5-Mistral-7B",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "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": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.1",
+  "use_cache": false,
+  "vocab_size": 32002
+}

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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "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",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}