Upload folder using huggingface_hub

README.md

@@ -0,0 +1,65 @@
+---
+license: cc-by-nc-4.0
+base_model: athirdpath/Harmonia-20B
+tags:
+- generated_from_trainer
+model-index:
+- name: lora
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<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
+
+This model is a fine-tuned version of [athirdpath/Harmonia-20B](https://huggingface.co/athirdpath/Harmonia-20B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4881
+
+## 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: 3.5e-05
+- train_batch_size: 3
+- eval_batch_size: 3
+- seed: 42
+- gradient_accumulation_steps: 3
+- total_train_batch_size: 9
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.5598        | 0.55  | 50   | 1.5816          |
+| 1.5384        | 1.08  | 100  | 1.5146          |
+| 1.5362        | 1.64  | 150  | 1.4972          |
+| 1.4234        | 2.17  | 200  | 1.4902          |
+| 1.4678        | 2.72  | 250  | 1.4881          |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.0.1+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "athirdpath/Harmonia-20B",
+  "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": 0.051,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 512,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a53a221e8689cb7760f2bc332f5353426de11e5769f2370ce5b677754d31997b
+size 12417558637

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

checkpoint-100/README.md

@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: athirdpath/Harmonia-20B
+---
+
+# 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]
+
+
+## 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": "athirdpath/Harmonia-20B",
+  "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": 0.051,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 512,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed2a5d4bad78fd2dc55f90676d267c1236aa8809218d5057ff9837f9a808e204
+size 12417357416

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b56fbcaef8544394b433d22a20e6ce7c40b1b4a8c16ff2ca4561afbafcbb3b0
+size 6221780007

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c64df358e209d2c50ed2a4471b1eb76e7036964a03006b9b39d8ee4f01901c5d
+size 14575

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4548ab2ca2259580fce479fb36c8dcb12e2641178c3263ca43aba9c53a990859
+size 627

checkpoint-100/trainer_state.json

@@ -0,0 +1,635 @@
+{
+  "best_metric": 1.5145553350448608,
+  "best_model_checkpoint": "./lora/checkpoint-100",
+  "epoch": 1.0845588235294117,
+  "eval_steps": 50,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.5e-06,
+      "loss": 1.9367,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 7e-06,
+      "loss": 2.0288,
+      "step": 2
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.05e-05,
+      "loss": 2.0352,
+      "step": 3
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.4e-05,
+      "loss": 2.0986,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.75e-05,
+      "loss": 2.0046,
+      "step": 5
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.1e-05,
+      "loss": 2.1414,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.4499999999999996e-05,
+      "loss": 1.9425,
+      "step": 7
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.8e-05,
+      "loss": 1.9751,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 3.15e-05,
+      "loss": 1.8964,
+      "step": 9
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 3.5e-05,
+      "loss": 1.9809,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.4998722514973183e-05,
+      "loss": 1.8772,
+      "step": 11
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.4994890246403374e-05,
+      "loss": 2.0195,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.498850375379522e-05,
+      "loss": 1.8636,
+      "step": 13
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.4979563969565714e-05,
+      "loss": 1.9242,
+      "step": 14
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 3.4968072198908054e-05,
+      "loss": 1.8237,
+      "step": 15
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 3.495403011960109e-05,
+      "loss": 1.9113,
+      "step": 16
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 3.493743978176438e-05,
+      "loss": 1.7741,
+      "step": 17
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 3.4918303607558846e-05,
+      "loss": 1.802,
+      "step": 18
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3.4896624390833185e-05,
+      "loss": 1.8119,
+      "step": 19
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 3.487240529671594e-05,
+      "loss": 1.8352,
+      "step": 20
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 3.484564986115341e-05,
+      "loss": 1.6615,
+      "step": 21
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 3.481636199039339e-05,
+      "loss": 1.6718,
+      "step": 22
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 3.478454596041491e-05,
+      "loss": 1.7832,
+      "step": 23
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 3.475020641630389e-05,
+      "loss": 1.7315,
+      "step": 24
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 3.4713348371575014e-05,
+      "loss": 1.6749,
+      "step": 25
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 3.4673977207439735e-05,
+      "loss": 1.652,
+      "step": 26
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 3.4632098672020644e-05,
+      "loss": 1.6948,
+      "step": 27
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.458771887951226e-05,
+      "loss": 1.6259,
+      "step": 28
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.4540844309288334e-05,
+      "loss": 1.7353,
+      "step": 29
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.449148180495591e-05,
+      "loss": 1.6788,
+      "step": 30
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.443963857335615e-05,
+      "loss": 1.6359,
+      "step": 31
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.438532218351215e-05,
+      "loss": 1.6468,
+      "step": 32
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.432854056552388e-05,
+      "loss": 1.6234,
+      "step": 33
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.426930200941041e-05,
+      "loss": 1.6664,
+      "step": 34
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.420761516389954e-05,
+      "loss": 1.6361,
+      "step": 35
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.414348903516519e-05,
+      "loss": 1.5885,
+      "step": 36
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.4076932985512385e-05,
+      "loss": 1.624,
+      "step": 37
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.40079567320105e-05,
+      "loss": 1.6071,
+      "step": 38
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.3936570345074515e-05,
+      "loss": 1.6047,
+      "step": 39
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.386278424699476e-05,
+      "loss": 1.6151,
+      "step": 40
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.378660921041529e-05,
+      "loss": 1.671,
+      "step": 41
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 3.3708056356761085e-05,
+      "loss": 1.539,
+      "step": 42
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.3627137154614375e-05,
+      "loss": 1.6051,
+      "step": 43
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 3.354386341804019e-05,
+      "loss": 1.6533,
+      "step": 44
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 3.345824730486158e-05,
+      "loss": 1.591,
+      "step": 45
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 3.337030131488454e-05,
+      "loss": 1.5887,
+      "step": 46
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 3.328003828807314e-05,
+      "loss": 1.6664,
+      "step": 47
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 3.318747140267481e-05,
+      "loss": 1.5403,
+      "step": 48
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 3.3092614173296436e-05,
+      "loss": 1.5699,
+      "step": 49
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 3.299548044893117e-05,
+      "loss": 1.5598,
+      "step": 50
+    },
+    {
+      "epoch": 0.55,
+      "eval_loss": 1.5816165208816528,
+      "eval_runtime": 80.8849,
+      "eval_samples_per_second": 8.32,
+      "eval_steps_per_second": 2.782,
+      "step": 50
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 3.289608441093656e-05,
+      "loss": 1.5841,
+      "step": 51
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 3.279444057096406e-05,
+      "loss": 1.6432,
+      "step": 52
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 3.2690563768840375e-05,
+      "loss": 1.6234,
+      "step": 53
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 3.258446917040086e-05,
+      "loss": 1.6125,
+      "step": 54
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 3.2476172265275326e-05,
+      "loss": 1.5279,
+      "step": 55
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.2365688864626616e-05,
+      "loss": 1.5377,
+      "step": 56
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.225303509884215e-05,
+      "loss": 1.6028,
+      "step": 57
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.213822741517896e-05,
+      "loss": 1.5977,
+      "step": 58
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.202128257536241e-05,
+      "loss": 1.566,
+      "step": 59
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.190221765313898e-05,
+      "loss": 1.4609,
+      "step": 60
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.178105003178358e-05,
+      "loss": 1.504,
+      "step": 61
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.1657797401561575e-05,
+      "loss": 1.5397,
+      "step": 62
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.153247775714607e-05,
+      "loss": 1.5508,
+      "step": 63
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.1405109394990694e-05,
+      "loss": 1.6191,
+      "step": 64
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.127571091065837e-05,
+      "loss": 1.5808,
+      "step": 65
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.1144301196106385e-05,
+      "loss": 1.5201,
+      "step": 66
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.101089943692819e-05,
+      "loss": 1.5121,
+      "step": 67
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.087552510955234e-05,
+      "loss": 1.6296,
+      "step": 68
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.0738197978398984e-05,
+      "loss": 1.5682,
+      "step": 69
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.059893809299426e-05,
+      "loss": 1.61,
+      "step": 70
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.045776578504316e-05,
+      "loss": 1.6149,
+      "step": 71
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.0314701665461036e-05,
+      "loss": 1.4799,
+      "step": 72
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.016976662136455e-05,
+      "loss": 1.4868,
+      "step": 73
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.0022981813022116e-05,
+      "loss": 1.5025,
+      "step": 74
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.9874368670764577e-05,
+      "loss": 1.6717,
+      "step": 75
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 2.97239488918564e-05,
+      "loss": 1.5035,
+      "step": 76
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.957174443732788e-05,
+      "loss": 1.5091,
+      "step": 77
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.941777752876895e-05,
+      "loss": 1.4939,
+      "step": 78
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.926207064508477e-05,
+      "loss": 1.5109,
+      "step": 79
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.9104646519213912e-05,
+      "loss": 1.5311,
+      "step": 80
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.8945528134809375e-05,
+      "loss": 1.5566,
+      "step": 81
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.8784738722882982e-05,
+      "loss": 1.5547,
+      "step": 82
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.8622301758413743e-05,
+      "loss": 1.5009,
+      "step": 83
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.8458240956920487e-05,
+      "loss": 1.5045,
+      "step": 84
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.8292580270999504e-05,
+      "loss": 1.5591,
+      "step": 85
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.8125343886827444e-05,
+      "loss": 1.5189,
+      "step": 86
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.7956556220630225e-05,
+      "loss": 1.5223,
+      "step": 87
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.7786241915118276e-05,
+      "loss": 1.5285,
+      "step": 88
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.761442583588876e-05,
+      "loss": 1.4655,
+      "step": 89
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.7441133067795224e-05,
+      "loss": 1.4867,
+      "step": 90
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.726638891128527e-05,
+      "loss": 1.4935,
+      "step": 91
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 2.7090218878706727e-05,
+      "loss": 1.4836,
+      "step": 92
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 2.6912648690582874e-05,
+      "loss": 1.4761,
+      "step": 93
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 2.673370427185732e-05,
+      "loss": 1.4982,
+      "step": 94
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 2.655341174810899e-05,
+      "loss": 1.5167,
+      "step": 95
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 2.6371797441737832e-05,
+      "loss": 1.5549,
+      "step": 96
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 2.6188887868121788e-05,
+      "loss": 1.4583,
+      "step": 97
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 2.6004709731745603e-05,
+      "loss": 1.5408,
+      "step": 98
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 2.581928992230203e-05,
+      "loss": 1.5641,
+      "step": 99
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.563265551076595e-05,
+      "loss": 1.5384,
+      "step": 100
+    },
+    {
+      "epoch": 1.08,
+      "eval_loss": 1.5145553350448608,
+      "eval_runtime": 80.9913,
+      "eval_samples_per_second": 8.31,
+      "eval_steps_per_second": 2.778,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 270,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 5.0671825762595635e+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:e94a8513683270122b1265e56d9d040f62da4cc344299c99bdac999537ecc104
+size 4539

checkpoint-200/README.md

@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: athirdpath/Harmonia-20B
+---
+
+# 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]
+
+
+## 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-200/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "athirdpath/Harmonia-20B",
+  "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": 0.051,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 512,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cc6ac2c3d0aef8f75dc7ecb1ffc02e8642588b980ebf0997257872bfd63e77c
+size 12417357416

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e152dbd072a6b269241ed53e7f6a81c6899803e9389cb22f50e9670c3316416
+size 6221780007

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e782a6a8cb5ac5e3bdcd5fc2ea19e16bb2fa2abab62ed6c702fd1656e11e2d3
+size 14575

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50461257780a0a23964c850bb05d4644e85ef7d4b69c301de9c38714ceb4f97d
+size 627

checkpoint-200/trainer_state.json

@@ -0,0 +1,1251 @@
+{
+  "best_metric": 1.4901626110076904,
+  "best_model_checkpoint": "./lora/checkpoint-200",
+  "epoch": 2.1691176470588234,
+  "eval_steps": 50,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.5e-06,
+      "loss": 1.9367,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 7e-06,
+      "loss": 2.0288,
+      "step": 2
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.05e-05,
+      "loss": 2.0352,
+      "step": 3
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.4e-05,
+      "loss": 2.0986,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.75e-05,
+      "loss": 2.0046,
+      "step": 5
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.1e-05,
+      "loss": 2.1414,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.4499999999999996e-05,
+      "loss": 1.9425,
+      "step": 7
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.8e-05,
+      "loss": 1.9751,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 3.15e-05,
+      "loss": 1.8964,
+      "step": 9
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 3.5e-05,
+      "loss": 1.9809,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.4998722514973183e-05,
+      "loss": 1.8772,
+      "step": 11
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.4994890246403374e-05,
+      "loss": 2.0195,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.498850375379522e-05,
+      "loss": 1.8636,
+      "step": 13
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.4979563969565714e-05,
+      "loss": 1.9242,
+      "step": 14
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 3.4968072198908054e-05,
+      "loss": 1.8237,
+      "step": 15
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 3.495403011960109e-05,
+      "loss": 1.9113,
+      "step": 16
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 3.493743978176438e-05,
+      "loss": 1.7741,
+      "step": 17
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 3.4918303607558846e-05,
+      "loss": 1.802,
+      "step": 18
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3.4896624390833185e-05,
+      "loss": 1.8119,
+      "step": 19
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 3.487240529671594e-05,
+      "loss": 1.8352,
+      "step": 20
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 3.484564986115341e-05,
+      "loss": 1.6615,
+      "step": 21
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 3.481636199039339e-05,
+      "loss": 1.6718,
+      "step": 22
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 3.478454596041491e-05,
+      "loss": 1.7832,
+      "step": 23
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 3.475020641630389e-05,
+      "loss": 1.7315,
+      "step": 24
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 3.4713348371575014e-05,
+      "loss": 1.6749,
+      "step": 25
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 3.4673977207439735e-05,
+      "loss": 1.652,
+      "step": 26
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 3.4632098672020644e-05,
+      "loss": 1.6948,
+      "step": 27
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.458771887951226e-05,
+      "loss": 1.6259,
+      "step": 28
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.4540844309288334e-05,
+      "loss": 1.7353,
+      "step": 29
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.449148180495591e-05,
+      "loss": 1.6788,
+      "step": 30
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.443963857335615e-05,
+      "loss": 1.6359,
+      "step": 31
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.438532218351215e-05,
+      "loss": 1.6468,
+      "step": 32
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.432854056552388e-05,
+      "loss": 1.6234,
+      "step": 33
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.426930200941041e-05,
+      "loss": 1.6664,
+      "step": 34
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.420761516389954e-05,
+      "loss": 1.6361,
+      "step": 35
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.414348903516519e-05,
+      "loss": 1.5885,
+      "step": 36
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.4076932985512385e-05,
+      "loss": 1.624,
+      "step": 37
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.40079567320105e-05,
+      "loss": 1.6071,
+      "step": 38
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.3936570345074515e-05,
+      "loss": 1.6047,
+      "step": 39
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.386278424699476e-05,
+      "loss": 1.6151,
+      "step": 40
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.378660921041529e-05,
+      "loss": 1.671,
+      "step": 41
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 3.3708056356761085e-05,
+      "loss": 1.539,
+      "step": 42
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.3627137154614375e-05,
+      "loss": 1.6051,
+      "step": 43
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 3.354386341804019e-05,
+      "loss": 1.6533,
+      "step": 44
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 3.345824730486158e-05,
+      "loss": 1.591,
+      "step": 45
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 3.337030131488454e-05,
+      "loss": 1.5887,
+      "step": 46
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 3.328003828807314e-05,
+      "loss": 1.6664,
+      "step": 47
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 3.318747140267481e-05,
+      "loss": 1.5403,
+      "step": 48
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 3.3092614173296436e-05,
+      "loss": 1.5699,
+      "step": 49
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 3.299548044893117e-05,
+      "loss": 1.5598,
+      "step": 50
+    },
+    {
+      "epoch": 0.55,
+      "eval_loss": 1.5816165208816528,
+      "eval_runtime": 80.8849,
+      "eval_samples_per_second": 8.32,
+      "eval_steps_per_second": 2.782,
+      "step": 50
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 3.289608441093656e-05,
+      "loss": 1.5841,
+      "step": 51
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 3.279444057096406e-05,
+      "loss": 1.6432,
+      "step": 52
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 3.2690563768840375e-05,
+      "loss": 1.6234,
+      "step": 53
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 3.258446917040086e-05,
+      "loss": 1.6125,
+      "step": 54
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 3.2476172265275326e-05,
+      "loss": 1.5279,
+      "step": 55
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.2365688864626616e-05,
+      "loss": 1.5377,
+      "step": 56
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.225303509884215e-05,
+      "loss": 1.6028,
+      "step": 57
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.213822741517896e-05,
+      "loss": 1.5977,
+      "step": 58
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.202128257536241e-05,
+      "loss": 1.566,
+      "step": 59
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.190221765313898e-05,
+      "loss": 1.4609,
+      "step": 60
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.178105003178358e-05,
+      "loss": 1.504,
+      "step": 61
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.1657797401561575e-05,
+      "loss": 1.5397,
+      "step": 62
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.153247775714607e-05,
+      "loss": 1.5508,
+      "step": 63
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.1405109394990694e-05,
+      "loss": 1.6191,
+      "step": 64
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.127571091065837e-05,
+      "loss": 1.5808,
+      "step": 65
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.1144301196106385e-05,
+      "loss": 1.5201,
+      "step": 66
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.101089943692819e-05,
+      "loss": 1.5121,
+      "step": 67
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.087552510955234e-05,
+      "loss": 1.6296,
+      "step": 68
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.0738197978398984e-05,
+      "loss": 1.5682,
+      "step": 69
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.059893809299426e-05,
+      "loss": 1.61,
+      "step": 70
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.045776578504316e-05,
+      "loss": 1.6149,
+      "step": 71
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.0314701665461036e-05,
+      "loss": 1.4799,
+      "step": 72
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.016976662136455e-05,
+      "loss": 1.4868,
+      "step": 73
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.0022981813022116e-05,
+      "loss": 1.5025,
+      "step": 74
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.9874368670764577e-05,
+      "loss": 1.6717,
+      "step": 75
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 2.97239488918564e-05,
+      "loss": 1.5035,
+      "step": 76
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.957174443732788e-05,
+      "loss": 1.5091,
+      "step": 77
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.941777752876895e-05,
+      "loss": 1.4939,
+      "step": 78
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.926207064508477e-05,
+      "loss": 1.5109,
+      "step": 79
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.9104646519213912e-05,
+      "loss": 1.5311,
+      "step": 80
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.8945528134809375e-05,
+      "loss": 1.5566,
+      "step": 81
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.8784738722882982e-05,
+      "loss": 1.5547,
+      "step": 82
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.8622301758413743e-05,
+      "loss": 1.5009,
+      "step": 83
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.8458240956920487e-05,
+      "loss": 1.5045,
+      "step": 84
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.8292580270999504e-05,
+      "loss": 1.5591,
+      "step": 85
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.8125343886827444e-05,
+      "loss": 1.5189,
+      "step": 86
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.7956556220630225e-05,
+      "loss": 1.5223,
+      "step": 87
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.7786241915118276e-05,
+      "loss": 1.5285,
+      "step": 88
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.761442583588876e-05,
+      "loss": 1.4655,
+      "step": 89
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.7441133067795224e-05,
+      "loss": 1.4867,
+      "step": 90
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.726638891128527e-05,
+      "loss": 1.4935,
+      "step": 91
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 2.7090218878706727e-05,
+      "loss": 1.4836,
+      "step": 92
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 2.6912648690582874e-05,
+      "loss": 1.4761,
+      "step": 93
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 2.673370427185732e-05,
+      "loss": 1.4982,
+      "step": 94
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 2.655341174810899e-05,
+      "loss": 1.5167,
+      "step": 95
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 2.6371797441737832e-05,
+      "loss": 1.5549,
+      "step": 96
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 2.6188887868121788e-05,
+      "loss": 1.4583,
+      "step": 97
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 2.6004709731745603e-05,
+      "loss": 1.5408,
+      "step": 98
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 2.581928992230203e-05,
+      "loss": 1.5641,
+      "step": 99
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.563265551076595e-05,
+      "loss": 1.5384,
+      "step": 100
+    },
+    {
+      "epoch": 1.08,
+      "eval_loss": 1.5145553350448608,
+      "eval_runtime": 80.9913,
+      "eval_samples_per_second": 8.31,
+      "eval_steps_per_second": 2.778,
+      "step": 100
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 2.5444833745442066e-05,
+      "loss": 1.6016,
+      "step": 101
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2.5255852047986722e-05,
+      "loss": 1.4881,
+      "step": 102
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.506573800940435e-05,
+      "loss": 1.4599,
+      "step": 103
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.487451938601926e-05,
+      "loss": 1.4524,
+      "step": 104
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2.4682224095423243e-05,
+      "loss": 1.4767,
+      "step": 105
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 2.448888021239967e-05,
+      "loss": 1.5478,
+      "step": 106
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 2.429451596482461e-05,
+      "loss": 1.5534,
+      "step": 107
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 2.4099159729545604e-05,
+      "loss": 1.5336,
+      "step": 108
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 2.3902840028238717e-05,
+      "loss": 1.5371,
+      "step": 109
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 2.370558552324437e-05,
+      "loss": 1.5404,
+      "step": 110
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 2.3507425013382768e-05,
+      "loss": 1.5516,
+      "step": 111
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 2.3308387429749247e-05,
+      "loss": 1.4838,
+      "step": 112
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 2.3108501831490418e-05,
+      "loss": 1.5548,
+      "step": 113
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 2.290779740156158e-05,
+      "loss": 1.4899,
+      "step": 114
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 2.2706303442466052e-05,
+      "loss": 1.5475,
+      "step": 115
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 2.2504049371977057e-05,
+      "loss": 1.5116,
+      "step": 116
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 2.23010647188428e-05,
+      "loss": 1.4947,
+      "step": 117
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 2.209737911847527e-05,
+      "loss": 1.5523,
+      "step": 118
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 2.189302230862358e-05,
+      "loss": 1.4629,
+      "step": 119
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 2.168802412503226e-05,
+      "loss": 1.5319,
+      "step": 120
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 2.148241449708532e-05,
+      "loss": 1.5934,
+      "step": 121
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 2.1276223443436606e-05,
+      "loss": 1.4876,
+      "step": 122
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 2.10694810676271e-05,
+      "loss": 1.4731,
+      "step": 123
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 2.0862217553689898e-05,
+      "loss": 1.5769,
+      "step": 124
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 2.065446316174335e-05,
+      "loss": 1.5752,
+      "step": 125
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 2.044624822357317e-05,
+      "loss": 1.4024,
+      "step": 126
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 2.023760313820404e-05,
+      "loss": 1.4952,
+      "step": 127
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 2.002855836746137e-05,
+      "loss": 1.4805,
+      "step": 128
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.9819144431523983e-05,
+      "loss": 1.3949,
+      "step": 129
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.960939190446815e-05,
+      "loss": 1.4833,
+      "step": 130
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.939933140980391e-05,
+      "loss": 1.5756,
+      "step": 131
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.9188993616004013e-05,
+      "loss": 1.4754,
+      "step": 132
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.8978409232026423e-05,
+      "loss": 1.5131,
+      "step": 133
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.8767609002830843e-05,
+      "loss": 1.52,
+      "step": 134
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.8556623704890005e-05,
+      "loss": 1.5587,
+      "step": 135
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.8345484141696373e-05,
+      "loss": 1.5522,
+      "step": 136
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.8134221139264865e-05,
+      "loss": 1.509,
+      "step": 137
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.7922865541632313e-05,
+      "loss": 1.5177,
+      "step": 138
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.77114482063543e-05,
+      "loss": 1.5096,
+      "step": 139
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.75e-05,
+      "loss": 1.578,
+      "step": 140
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.7288551793645696e-05,
+      "loss": 1.5456,
+      "step": 141
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.7077134458367687e-05,
+      "loss": 1.5606,
+      "step": 142
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1.686577886073514e-05,
+      "loss": 1.5104,
+      "step": 143
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1.6654515858303628e-05,
+      "loss": 1.4819,
+      "step": 144
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1.644337629510999e-05,
+      "loss": 1.535,
+      "step": 145
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1.6232390997169158e-05,
+      "loss": 1.4451,
+      "step": 146
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.6021590767973577e-05,
+      "loss": 1.4682,
+      "step": 147
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.5811006383995984e-05,
+      "loss": 1.4697,
+      "step": 148
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.5600668590196092e-05,
+      "loss": 1.4647,
+      "step": 149
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.539060809553185e-05,
+      "loss": 1.5362,
+      "step": 150
+    },
+    {
+      "epoch": 1.64,
+      "eval_loss": 1.4972482919692993,
+      "eval_runtime": 81.0124,
+      "eval_samples_per_second": 8.307,
+      "eval_steps_per_second": 2.777,
+      "step": 150
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.5180855568476021e-05,
+      "loss": 1.4905,
+      "step": 151
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.497144163253863e-05,
+      "loss": 1.4896,
+      "step": 152
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.4762396861795956e-05,
+      "loss": 1.5663,
+      "step": 153
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.4553751776426824e-05,
+      "loss": 1.42,
+      "step": 154
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.4345536838256648e-05,
+      "loss": 1.4287,
+      "step": 155
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.4137782446310101e-05,
+      "loss": 1.4805,
+      "step": 156
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.3930518932372898e-05,
+      "loss": 1.5101,
+      "step": 157
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.3723776556563393e-05,
+      "loss": 1.4862,
+      "step": 158
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 1.3517585502914675e-05,
+      "loss": 1.4456,
+      "step": 159
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.3311975874967744e-05,
+      "loss": 1.5431,
+      "step": 160
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.3106977691376419e-05,
+      "loss": 1.5328,
+      "step": 161
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.2902620881524727e-05,
+      "loss": 1.4515,
+      "step": 162
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.2698935281157198e-05,
+      "loss": 1.4825,
+      "step": 163
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.249595062802294e-05,
+      "loss": 1.3762,
+      "step": 164
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.229369655753395e-05,
+      "loss": 1.4809,
+      "step": 165
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.2092202598438421e-05,
+      "loss": 1.4052,
+      "step": 166
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.1891498168509584e-05,
+      "loss": 1.4222,
+      "step": 167
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.1691612570250755e-05,
+      "loss": 1.4845,
+      "step": 168
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 1.1492574986617227e-05,
+      "loss": 1.4941,
+      "step": 169
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.1294414476755625e-05,
+      "loss": 1.4441,
+      "step": 170
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.1097159971761285e-05,
+      "loss": 1.5222,
+      "step": 171
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.0900840270454391e-05,
+      "loss": 1.4522,
+      "step": 172
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.0705484035175387e-05,
+      "loss": 1.5283,
+      "step": 173
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.051111978760033e-05,
+      "loss": 1.4071,
+      "step": 174
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.0317775904576759e-05,
+      "loss": 1.4695,
+      "step": 175
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.0125480613980743e-05,
+      "loss": 1.436,
+      "step": 176
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 9.934261990595642e-06,
+      "loss": 1.5197,
+      "step": 177
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 9.744147952013278e-06,
+      "loss": 1.5146,
+      "step": 178
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 9.55516625455793e-06,
+      "loss": 1.5029,
+      "step": 179
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 9.36734448923405e-06,
+      "loss": 1.41,
+      "step": 180
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 9.180710077697967e-06,
+      "loss": 1.548,
+      "step": 181
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 8.995290268254394e-06,
+      "loss": 1.5132,
+      "step": 182
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8.811112131878218e-06,
+      "loss": 1.4268,
+      "step": 183
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 8.628202558262172e-06,
+      "loss": 1.5041,
+      "step": 184
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8.446588251891004e-06,
+      "loss": 1.4452,
+      "step": 185
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 8.266295728142675e-06,
+      "loss": 1.5405,
+      "step": 186
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 8.087351309417123e-06,
+      "loss": 1.4638,
+      "step": 187
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 7.909781121293278e-06,
+      "loss": 1.497,
+      "step": 188
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 7.733611088714731e-06,
+      "loss": 1.502,
+      "step": 189
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 7.558866932204775e-06,
+      "loss": 1.4087,
+      "step": 190
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 7.385574164111238e-06,
+      "loss": 1.5167,
+      "step": 191
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 7.213758084881722e-06,
+      "loss": 1.4645,
+      "step": 192
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 7.043443779369772e-06,
+      "loss": 1.4866,
+      "step": 193
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 6.874656113172554e-06,
+      "loss": 1.5312,
+      "step": 194
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 6.707419729000496e-06,
+      "loss": 1.4727,
+      "step": 195
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 6.54175904307951e-06,
+      "loss": 1.4668,
+      "step": 196
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 6.3776982415862576e-06,
+      "loss": 1.455,
+      "step": 197
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 6.215261277117018e-06,
+      "loss": 1.4442,
+      "step": 198
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 6.054471865190627e-06,
+      "loss": 1.4379,
+      "step": 199
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 5.895353480786087e-06,
+      "loss": 1.4234,
+      "step": 200
+    },
+    {
+      "epoch": 2.17,
+      "eval_loss": 1.4901626110076904,
+      "eval_runtime": 80.9626,
+      "eval_samples_per_second": 8.312,
+      "eval_steps_per_second": 2.779,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 270,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 1.0140001618121196e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e94a8513683270122b1265e56d9d040f62da4cc344299c99bdac999537ecc104
+size 4539

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "athirdpath/Harmonia-20B",
+  "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": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 62,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "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,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.35.2",
+  "use_cache": false,
+  "vocab_size": 32001
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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 +1,52 @@
+{
+  "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": "[PAD]",
+      "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": 2048,
+  "pad_token": "[PAD]",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}