Upload folder using huggingface_hub

README.md

@@ -0,0 +1,67 @@
+---
+license: cc-by-nc-4.0
+base_model: NeverSleep/Nethena-20B
+tags:
+- generated_from_trainer
+model-index:
+- name: lora-outA
+  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-outA
+
+This model is a fine-tuned version of [NeverSleep/Nethena-20B](https://huggingface.co/NeverSleep/Nethena-20B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3864
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 5
+- total_train_batch_size: 20
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.955         | 0.38  | 25   | 1.9037          |
+| 1.6598        | 0.75  | 50   | 1.6192          |
+| 1.5649        | 1.13  | 75   | 1.5010          |
+| 1.4424        | 1.5   | 100  | 1.4424          |
+| 1.4142        | 1.88  | 125  | 1.4068          |
+| 1.4951        | 2.25  | 150  | 1.3908          |
+| 1.4418        | 2.63  | 175  | 1.3864          |
+
+
+### 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": "NeverSleep/Nethena-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": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:140728eaa0d9e55ac441f43561217ae3a5f5418f15f6f39f0eb4db134df4d121
+size 3104623258

added_tokens.json

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

checkpoint-100/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: NeverSleep/Nethena-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]
+- **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": "NeverSleep/Nethena-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": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-100/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:516b68e7fa801cdabae76dbc60c262b9aade6fb786f0c8c3834057b2bfc3c797
+size 3104623258

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05aa8f439bc98fcd0bbdc5f6c5602cf84651b914a0a308508d0ce037dc3013b4
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a75f5757cc9f57a8b09def7459ca6f5de638c11ce7af9155325efdd1595b753b
+size 1064

checkpoint-100/trainer_state.json

@@ -0,0 +1,651 @@
+{
+  "best_metric": 1.44235098361969,
+  "best_model_checkpoint": "./lora-outA/checkpoint-100",
+  "epoch": 1.5015015015015014,
+  "eval_steps": 25,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.027,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.0877,
+      "step": 2
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6e-06,
+      "loss": 2.4458,
+      "step": 3
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.2379,
+      "step": 4
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1e-05,
+      "loss": 2.4292,
+      "step": 5
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.2e-05,
+      "loss": 2.0784,
+      "step": 6
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.4e-05,
+      "loss": 2.1768,
+      "step": 7
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.0902,
+      "step": 8
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.8e-05,
+      "loss": 2.3488,
+      "step": 9
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2e-05,
+      "loss": 2.3467,
+      "step": 10
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9998603811858573e-05,
+      "loss": 1.9468,
+      "step": 11
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9994415637302545e-05,
+      "loss": 2.2701,
+      "step": 12
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.998743664582786e-05,
+      "loss": 2.1306,
+      "step": 13
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9977668786231536e-05,
+      "loss": 2.2113,
+      "step": 14
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9965114786067515e-05,
+      "loss": 2.2447,
+      "step": 15
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.994977815088504e-05,
+      "loss": 1.9715,
+      "step": 16
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9931663163249744e-05,
+      "loss": 2.1725,
+      "step": 17
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9910774881547803e-05,
+      "loss": 1.9481,
+      "step": 18
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9887119138573462e-05,
+      "loss": 1.9348,
+      "step": 19
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9860702539900288e-05,
+      "loss": 2.1486,
+      "step": 20
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9831532462036634e-05,
+      "loss": 1.8827,
+      "step": 21
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.979961705036587e-05,
+      "loss": 1.8206,
+      "step": 22
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9764965216871848e-05,
+      "loss": 2.1399,
+      "step": 23
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9727586637650373e-05,
+      "loss": 1.807,
+      "step": 24
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9687491750207255e-05,
+      "loss": 1.955,
+      "step": 25
+    },
+    {
+      "epoch": 0.38,
+      "eval_loss": 1.9037058353424072,
+      "eval_runtime": 10.8675,
+      "eval_samples_per_second": 2.576,
+      "eval_steps_per_second": 0.644,
+      "step": 25
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.964469175054377e-05,
+      "loss": 1.8608,
+      "step": 26
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9599198590030308e-05,
+      "loss": 2.1292,
+      "step": 27
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9551024972069127e-05,
+      "loss": 1.9422,
+      "step": 28
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.950018434854704e-05,
+      "loss": 1.846,
+      "step": 29
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.944669091607919e-05,
+      "loss": 1.8679,
+      "step": 30
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9390559612044783e-05,
+      "loss": 1.7104,
+      "step": 31
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9331806110416027e-05,
+      "loss": 1.7278,
+      "step": 32
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9270446817381377e-05,
+      "loss": 2.0227,
+      "step": 33
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.920649886676429e-05,
+      "loss": 1.8487,
+      "step": 34
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.9139980115238827e-05,
+      "loss": 1.6051,
+      "step": 35
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.907090913734341e-05,
+      "loss": 1.6792,
+      "step": 36
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.899930522029408e-05,
+      "loss": 1.9176,
+      "step": 37
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.8925188358598815e-05,
+      "loss": 1.629,
+      "step": 38
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8848579248474286e-05,
+      "loss": 1.8579,
+      "step": 39
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8769499282066716e-05,
+      "loss": 1.6583,
+      "step": 40
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.8687970541478367e-05,
+      "loss": 1.7202,
+      "step": 41
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8604015792601395e-05,
+      "loss": 1.7408,
+      "step": 42
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.851765847876076e-05,
+      "loss": 1.7131,
+      "step": 43
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.842892271416797e-05,
+      "loss": 1.7969,
+      "step": 44
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.8337833277187472e-05,
+      "loss": 1.6165,
+      "step": 45
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.8244415603417603e-05,
+      "loss": 1.6652,
+      "step": 46
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.8148695778588034e-05,
+      "loss": 1.7009,
+      "step": 47
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.8050700531275632e-05,
+      "loss": 2.0433,
+      "step": 48
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.795045722544083e-05,
+      "loss": 1.577,
+      "step": 49
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.7847993852786612e-05,
+      "loss": 1.6598,
+      "step": 50
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 1.6191542148590088,
+      "eval_runtime": 10.8699,
+      "eval_samples_per_second": 2.576,
+      "eval_steps_per_second": 0.644,
+      "step": 50
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.7743339024942135e-05,
+      "loss": 1.7067,
+      "step": 51
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.7636521965473324e-05,
+      "loss": 1.6212,
+      "step": 52
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.7527572501722516e-05,
+      "loss": 1.5661,
+      "step": 53
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7416521056479577e-05,
+      "loss": 1.5579,
+      "step": 54
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.7303398639486696e-05,
+      "loss": 1.6506,
+      "step": 55
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.7188236838779297e-05,
+      "loss": 1.7512,
+      "step": 56
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 1.6908,
+      "step": 57
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6951924276746425e-05,
+      "loss": 1.778,
+      "step": 58
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.683083950278031e-05,
+      "loss": 1.451,
+      "step": 59
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.6707847301392237e-05,
+      "loss": 1.7809,
+      "step": 60
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6582982016632818e-05,
+      "loss": 1.6405,
+      "step": 61
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.6456278515588023e-05,
+      "loss": 1.6913,
+      "step": 62
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.6327772178642986e-05,
+      "loss": 1.7667,
+      "step": 63
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.619749888960245e-05,
+      "loss": 1.4675,
+      "step": 64
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.6065495025670675e-05,
+      "loss": 1.5044,
+      "step": 65
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5931797447293553e-05,
+      "loss": 1.6187,
+      "step": 66
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.5796443487865774e-05,
+      "loss": 1.6726,
+      "step": 67
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.5659470943305956e-05,
+      "loss": 1.5999,
+      "step": 68
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.552091806150257e-05,
+      "loss": 1.4913,
+      "step": 69
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.5380823531633727e-05,
+      "loss": 1.4692,
+      "step": 70
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.523922647336369e-05,
+      "loss": 1.5326,
+      "step": 71
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.5096166425919176e-05,
+      "loss": 1.4767,
+      "step": 72
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.4951683337048536e-05,
+      "loss": 1.3673,
+      "step": 73
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.4805817551866839e-05,
+      "loss": 1.6663,
+      "step": 74
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.4658609801589982e-05,
+      "loss": 1.5649,
+      "step": 75
+    },
+    {
+      "epoch": 1.13,
+      "eval_loss": 1.5010281801223755,
+      "eval_runtime": 10.8975,
+      "eval_samples_per_second": 2.569,
+      "eval_steps_per_second": 0.642,
+      "step": 75
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.451010119216102e-05,
+      "loss": 1.4662,
+      "step": 76
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.436033319277183e-05,
+      "loss": 1.5699,
+      "step": 77
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.4209347624283352e-05,
+      "loss": 1.5471,
+      "step": 78
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.4057186647547638e-05,
+      "loss": 1.5028,
+      "step": 79
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.3903892751634949e-05,
+      "loss": 1.6067,
+      "step": 80
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.3749508741969213e-05,
+      "loss": 1.5703,
+      "step": 81
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.3594077728375129e-05,
+      "loss": 1.4915,
+      "step": 82
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.3437643113040302e-05,
+      "loss": 1.4674,
+      "step": 83
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.328024857839569e-05,
+      "loss": 1.6161,
+      "step": 84
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.3121938074917866e-05,
+      "loss": 1.5415,
+      "step": 85
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.2962755808856341e-05,
+      "loss": 1.4845,
+      "step": 86
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.2802746229889563e-05,
+      "loss": 1.3974,
+      "step": 87
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.2641954018712863e-05,
+      "loss": 1.5752,
+      "step": 88
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.2480424074561934e-05,
+      "loss": 1.856,
+      "step": 89
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.2318201502675285e-05,
+      "loss": 1.4777,
+      "step": 90
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.2155331601699136e-05,
+      "loss": 1.4124,
+      "step": 91
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.1991859851038362e-05,
+      "loss": 1.3642,
+      "step": 92
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.1827831898156905e-05,
+      "loss": 1.4942,
+      "step": 93
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1663293545831302e-05,
+      "loss": 1.5128,
+      "step": 94
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1498290739360815e-05,
+      "loss": 1.5812,
+      "step": 95
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.133286955373779e-05,
+      "loss": 1.5092,
+      "step": 96
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.1167076180781764e-05,
+      "loss": 1.4185,
+      "step": 97
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.1000956916240985e-05,
+      "loss": 1.6486,
+      "step": 98
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.08345581468649e-05,
+      "loss": 1.5457,
+      "step": 99
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0667926337451217e-05,
+      "loss": 1.4424,
+      "step": 100
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 1.44235098361969,
+      "eval_runtime": 10.8826,
+      "eval_samples_per_second": 2.573,
+      "eval_steps_per_second": 0.643,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 198,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "total_flos": 2.572653895310377e+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:d7fec19a554d0970f5e2dbe43273fbdb3e1b9cdfff23ccd1e725620293a85c95
+size 4920

checkpoint-150/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: NeverSleep/Nethena-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]
+- **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": "NeverSleep/Nethena-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": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-150/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:140728eaa0d9e55ac441f43561217ae3a5f5418f15f6f39f0eb4db134df4d121
+size 3104623258

checkpoint-150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afde7d54c1e1c7773c0f916e50a456c335d358363c6015cec196b5300924e2b5
+size 6209163710

checkpoint-150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7488f2f71288bda404be5ac85c9d726d9fc20418dcdd1cae5181560a868aade0
+size 14244

checkpoint-150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a74a61eed41363201576a2c2f03096955a771b7df8fef34afee819f593b995f
+size 1064

checkpoint-150/trainer_state.json

@@ -0,0 +1,967 @@
+{
+  "best_metric": 1.3908014297485352,
+  "best_model_checkpoint": "./lora-outA/checkpoint-150",
+  "epoch": 2.2522522522522523,
+  "eval_steps": 25,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.027,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.0877,
+      "step": 2
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6e-06,
+      "loss": 2.4458,
+      "step": 3
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.2379,
+      "step": 4
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1e-05,
+      "loss": 2.4292,
+      "step": 5
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.2e-05,
+      "loss": 2.0784,
+      "step": 6
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.4e-05,
+      "loss": 2.1768,
+      "step": 7
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.0902,
+      "step": 8
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.8e-05,
+      "loss": 2.3488,
+      "step": 9
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2e-05,
+      "loss": 2.3467,
+      "step": 10
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9998603811858573e-05,
+      "loss": 1.9468,
+      "step": 11
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9994415637302545e-05,
+      "loss": 2.2701,
+      "step": 12
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.998743664582786e-05,
+      "loss": 2.1306,
+      "step": 13
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9977668786231536e-05,
+      "loss": 2.2113,
+      "step": 14
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9965114786067515e-05,
+      "loss": 2.2447,
+      "step": 15
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.994977815088504e-05,
+      "loss": 1.9715,
+      "step": 16
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9931663163249744e-05,
+      "loss": 2.1725,
+      "step": 17
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9910774881547803e-05,
+      "loss": 1.9481,
+      "step": 18
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9887119138573462e-05,
+      "loss": 1.9348,
+      "step": 19
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9860702539900288e-05,
+      "loss": 2.1486,
+      "step": 20
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9831532462036634e-05,
+      "loss": 1.8827,
+      "step": 21
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.979961705036587e-05,
+      "loss": 1.8206,
+      "step": 22
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9764965216871848e-05,
+      "loss": 2.1399,
+      "step": 23
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9727586637650373e-05,
+      "loss": 1.807,
+      "step": 24
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9687491750207255e-05,
+      "loss": 1.955,
+      "step": 25
+    },
+    {
+      "epoch": 0.38,
+      "eval_loss": 1.9037058353424072,
+      "eval_runtime": 10.8675,
+      "eval_samples_per_second": 2.576,
+      "eval_steps_per_second": 0.644,
+      "step": 25
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.964469175054377e-05,
+      "loss": 1.8608,
+      "step": 26
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9599198590030308e-05,
+      "loss": 2.1292,
+      "step": 27
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9551024972069127e-05,
+      "loss": 1.9422,
+      "step": 28
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.950018434854704e-05,
+      "loss": 1.846,
+      "step": 29
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.944669091607919e-05,
+      "loss": 1.8679,
+      "step": 30
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9390559612044783e-05,
+      "loss": 1.7104,
+      "step": 31
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9331806110416027e-05,
+      "loss": 1.7278,
+      "step": 32
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9270446817381377e-05,
+      "loss": 2.0227,
+      "step": 33
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.920649886676429e-05,
+      "loss": 1.8487,
+      "step": 34
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.9139980115238827e-05,
+      "loss": 1.6051,
+      "step": 35
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.907090913734341e-05,
+      "loss": 1.6792,
+      "step": 36
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.899930522029408e-05,
+      "loss": 1.9176,
+      "step": 37
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.8925188358598815e-05,
+      "loss": 1.629,
+      "step": 38
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8848579248474286e-05,
+      "loss": 1.8579,
+      "step": 39
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8769499282066716e-05,
+      "loss": 1.6583,
+      "step": 40
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.8687970541478367e-05,
+      "loss": 1.7202,
+      "step": 41
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8604015792601395e-05,
+      "loss": 1.7408,
+      "step": 42
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.851765847876076e-05,
+      "loss": 1.7131,
+      "step": 43
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.842892271416797e-05,
+      "loss": 1.7969,
+      "step": 44
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.8337833277187472e-05,
+      "loss": 1.6165,
+      "step": 45
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.8244415603417603e-05,
+      "loss": 1.6652,
+      "step": 46
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.8148695778588034e-05,
+      "loss": 1.7009,
+      "step": 47
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.8050700531275632e-05,
+      "loss": 2.0433,
+      "step": 48
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.795045722544083e-05,
+      "loss": 1.577,
+      "step": 49
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.7847993852786612e-05,
+      "loss": 1.6598,
+      "step": 50
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 1.6191542148590088,
+      "eval_runtime": 10.8699,
+      "eval_samples_per_second": 2.576,
+      "eval_steps_per_second": 0.644,
+      "step": 50
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.7743339024942135e-05,
+      "loss": 1.7067,
+      "step": 51
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.7636521965473324e-05,
+      "loss": 1.6212,
+      "step": 52
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.7527572501722516e-05,
+      "loss": 1.5661,
+      "step": 53
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7416521056479577e-05,
+      "loss": 1.5579,
+      "step": 54
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.7303398639486696e-05,
+      "loss": 1.6506,
+      "step": 55
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.7188236838779297e-05,
+      "loss": 1.7512,
+      "step": 56
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 1.6908,
+      "step": 57
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6951924276746425e-05,
+      "loss": 1.778,
+      "step": 58
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.683083950278031e-05,
+      "loss": 1.451,
+      "step": 59
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.6707847301392237e-05,
+      "loss": 1.7809,
+      "step": 60
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6582982016632818e-05,
+      "loss": 1.6405,
+      "step": 61
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.6456278515588023e-05,
+      "loss": 1.6913,
+      "step": 62
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.6327772178642986e-05,
+      "loss": 1.7667,
+      "step": 63
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.619749888960245e-05,
+      "loss": 1.4675,
+      "step": 64
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.6065495025670675e-05,
+      "loss": 1.5044,
+      "step": 65
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5931797447293553e-05,
+      "loss": 1.6187,
+      "step": 66
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.5796443487865774e-05,
+      "loss": 1.6726,
+      "step": 67
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.5659470943305956e-05,
+      "loss": 1.5999,
+      "step": 68
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.552091806150257e-05,
+      "loss": 1.4913,
+      "step": 69
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.5380823531633727e-05,
+      "loss": 1.4692,
+      "step": 70
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.523922647336369e-05,
+      "loss": 1.5326,
+      "step": 71
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.5096166425919176e-05,
+      "loss": 1.4767,
+      "step": 72
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.4951683337048536e-05,
+      "loss": 1.3673,
+      "step": 73
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.4805817551866839e-05,
+      "loss": 1.6663,
+      "step": 74
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.4658609801589982e-05,
+      "loss": 1.5649,
+      "step": 75
+    },
+    {
+      "epoch": 1.13,
+      "eval_loss": 1.5010281801223755,
+      "eval_runtime": 10.8975,
+      "eval_samples_per_second": 2.569,
+      "eval_steps_per_second": 0.642,
+      "step": 75
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.451010119216102e-05,
+      "loss": 1.4662,
+      "step": 76
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.436033319277183e-05,
+      "loss": 1.5699,
+      "step": 77
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.4209347624283352e-05,
+      "loss": 1.5471,
+      "step": 78
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.4057186647547638e-05,
+      "loss": 1.5028,
+      "step": 79
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.3903892751634949e-05,
+      "loss": 1.6067,
+      "step": 80
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.3749508741969213e-05,
+      "loss": 1.5703,
+      "step": 81
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.3594077728375129e-05,
+      "loss": 1.4915,
+      "step": 82
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.3437643113040302e-05,
+      "loss": 1.4674,
+      "step": 83
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.328024857839569e-05,
+      "loss": 1.6161,
+      "step": 84
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.3121938074917866e-05,
+      "loss": 1.5415,
+      "step": 85
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.2962755808856341e-05,
+      "loss": 1.4845,
+      "step": 86
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.2802746229889563e-05,
+      "loss": 1.3974,
+      "step": 87
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.2641954018712863e-05,
+      "loss": 1.5752,
+      "step": 88
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.2480424074561934e-05,
+      "loss": 1.856,
+      "step": 89
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.2318201502675285e-05,
+      "loss": 1.4777,
+      "step": 90
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.2155331601699136e-05,
+      "loss": 1.4124,
+      "step": 91
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.1991859851038362e-05,
+      "loss": 1.3642,
+      "step": 92
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.1827831898156905e-05,
+      "loss": 1.4942,
+      "step": 93
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1663293545831302e-05,
+      "loss": 1.5128,
+      "step": 94
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1498290739360815e-05,
+      "loss": 1.5812,
+      "step": 95
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.133286955373779e-05,
+      "loss": 1.5092,
+      "step": 96
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.1167076180781764e-05,
+      "loss": 1.4185,
+      "step": 97
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.1000956916240985e-05,
+      "loss": 1.6486,
+      "step": 98
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.08345581468649e-05,
+      "loss": 1.5457,
+      "step": 99
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0667926337451217e-05,
+      "loss": 1.4424,
+      "step": 100
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 1.44235098361969,
+      "eval_runtime": 10.8826,
+      "eval_samples_per_second": 2.573,
+      "eval_steps_per_second": 0.643,
+      "step": 100
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0501108017871193e-05,
+      "loss": 1.5011,
+      "step": 101
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.0334149770076747e-05,
+      "loss": 1.5162,
+      "step": 102
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.016709821509301e-05,
+      "loss": 1.4612,
+      "step": 103
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1e-05,
+      "loss": 1.4465,
+      "step": 104
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.83290178490699e-06,
+      "loss": 1.7689,
+      "step": 105
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 9.665850229923258e-06,
+      "loss": 1.4932,
+      "step": 106
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.498891982128809e-06,
+      "loss": 1.524,
+      "step": 107
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.332073662548785e-06,
+      "loss": 1.4308,
+      "step": 108
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.165441853135104e-06,
+      "loss": 1.5015,
+      "step": 109
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 8.999043083759016e-06,
+      "loss": 1.6896,
+      "step": 110
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.832923819218238e-06,
+      "loss": 1.4334,
+      "step": 111
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 8.667130446262214e-06,
+      "loss": 1.342,
+      "step": 112
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8.501709260639187e-06,
+      "loss": 1.6292,
+      "step": 113
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.336706454168701e-06,
+      "loss": 1.3967,
+      "step": 114
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 8.1721681018431e-06,
+      "loss": 1.3275,
+      "step": 115
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 8.008140148961642e-06,
+      "loss": 1.3956,
+      "step": 116
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.844668398300866e-06,
+      "loss": 1.4647,
+      "step": 117
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.681798497324717e-06,
+      "loss": 1.4231,
+      "step": 118
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 7.5195759254380674e-06,
+      "loss": 1.4382,
+      "step": 119
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.358045981287141e-06,
+      "loss": 1.4577,
+      "step": 120
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 7.197253770110438e-06,
+      "loss": 1.4717,
+      "step": 121
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 7.037244191143662e-06,
+      "loss": 1.4299,
+      "step": 122
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 6.878061925082138e-06,
+      "loss": 1.5763,
+      "step": 123
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.719751421604309e-06,
+      "loss": 1.3964,
+      "step": 124
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 6.562356886959704e-06,
+      "loss": 1.4142,
+      "step": 125
+    },
+    {
+      "epoch": 1.88,
+      "eval_loss": 1.4067628383636475,
+      "eval_runtime": 10.8837,
+      "eval_samples_per_second": 2.573,
+      "eval_steps_per_second": 0.643,
+      "step": 125
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 6.405922271624874e-06,
+      "loss": 1.397,
+      "step": 126
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 6.2504912580307905e-06,
+      "loss": 1.5261,
+      "step": 127
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 6.0961072483650526e-06,
+      "loss": 1.4375,
+      "step": 128
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 5.942813352452365e-06,
+      "loss": 1.4193,
+      "step": 129
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 5.790652375716653e-06,
+      "loss": 1.5296,
+      "step": 130
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 5.6396668072281745e-06,
+      "loss": 1.4173,
+      "step": 131
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.48989880783898e-06,
+      "loss": 1.5766,
+      "step": 132
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.3413901984100195e-06,
+      "loss": 1.4055,
+      "step": 133
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 5.194182448133163e-06,
+      "loss": 1.2706,
+      "step": 134
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 5.0483166629514654e-06,
+      "loss": 1.4166,
+      "step": 135
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 4.903833574080825e-06,
+      "loss": 1.3389,
+      "step": 136
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 4.760773526636315e-06,
+      "loss": 1.472,
+      "step": 137
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 4.619176468366274e-06,
+      "loss": 1.3816,
+      "step": 138
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.479081938497435e-06,
+      "loss": 1.3801,
+      "step": 139
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 4.3405290566940475e-06,
+      "loss": 1.2649,
+      "step": 140
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 4.203556512134225e-06,
+      "loss": 1.3603,
+      "step": 141
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 4.0682025527064486e-06,
+      "loss": 1.2548,
+      "step": 142
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 3.934504974329326e-06,
+      "loss": 1.5477,
+      "step": 143
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 3.802501110397553e-06,
+      "loss": 1.3545,
+      "step": 144
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 3.672227821357014e-06,
+      "loss": 1.3932,
+      "step": 145
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 3.543721484411976e-06,
+      "loss": 1.5203,
+      "step": 146
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 3.4170179833671847e-06,
+      "loss": 1.4399,
+      "step": 147
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.292152698607768e-06,
+      "loss": 1.3587,
+      "step": 148
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 3.1691604972196922e-06,
+      "loss": 1.4239,
+      "step": 149
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 3.0480757232535773e-06,
+      "loss": 1.4951,
+      "step": 150
+    },
+    {
+      "epoch": 2.25,
+      "eval_loss": 1.3908014297485352,
+      "eval_runtime": 10.8882,
+      "eval_samples_per_second": 2.572,
+      "eval_steps_per_second": 0.643,
+      "step": 150
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 198,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "total_flos": 3.848852284322611e+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:d7fec19a554d0970f5e2dbe43273fbdb3e1b9cdfff23ccd1e725620293a85c95
+size 4920

checkpoint-50/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: NeverSleep/Nethena-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]
+- **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": "NeverSleep/Nethena-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": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-50/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f9ac549081cdec9bb66c33421680b90b24e134da058b0d7f97e0dc81e0ceb1c
+size 3104623258

checkpoint-50/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:029ace5cfb002e0798b48af45e984c8a0194d05c94765f611ffc4e478590a9e8
+size 14244

checkpoint-50/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1e419d8dfb642bf534e4b089d281b7e0b6457edf7928defa65e7880d55980eb
+size 1064

checkpoint-50/trainer_state.json

@@ -0,0 +1,335 @@
+{
+  "best_metric": 1.6191542148590088,
+  "best_model_checkpoint": "./lora-outA/checkpoint-50",
+  "epoch": 0.7507507507507507,
+  "eval_steps": 25,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.027,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.0877,
+      "step": 2
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6e-06,
+      "loss": 2.4458,
+      "step": 3
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.2379,
+      "step": 4
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1e-05,
+      "loss": 2.4292,
+      "step": 5
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.2e-05,
+      "loss": 2.0784,
+      "step": 6
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.4e-05,
+      "loss": 2.1768,
+      "step": 7
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.0902,
+      "step": 8
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.8e-05,
+      "loss": 2.3488,
+      "step": 9
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2e-05,
+      "loss": 2.3467,
+      "step": 10
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9998603811858573e-05,
+      "loss": 1.9468,
+      "step": 11
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9994415637302545e-05,
+      "loss": 2.2701,
+      "step": 12
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.998743664582786e-05,
+      "loss": 2.1306,
+      "step": 13
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9977668786231536e-05,
+      "loss": 2.2113,
+      "step": 14
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9965114786067515e-05,
+      "loss": 2.2447,
+      "step": 15
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.994977815088504e-05,
+      "loss": 1.9715,
+      "step": 16
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9931663163249744e-05,
+      "loss": 2.1725,
+      "step": 17
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9910774881547803e-05,
+      "loss": 1.9481,
+      "step": 18
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9887119138573462e-05,
+      "loss": 1.9348,
+      "step": 19
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9860702539900288e-05,
+      "loss": 2.1486,
+      "step": 20
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9831532462036634e-05,
+      "loss": 1.8827,
+      "step": 21
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.979961705036587e-05,
+      "loss": 1.8206,
+      "step": 22
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9764965216871848e-05,
+      "loss": 2.1399,
+      "step": 23
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9727586637650373e-05,
+      "loss": 1.807,
+      "step": 24
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9687491750207255e-05,
+      "loss": 1.955,
+      "step": 25
+    },
+    {
+      "epoch": 0.38,
+      "eval_loss": 1.9037058353424072,
+      "eval_runtime": 10.8675,
+      "eval_samples_per_second": 2.576,
+      "eval_steps_per_second": 0.644,
+      "step": 25
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.964469175054377e-05,
+      "loss": 1.8608,
+      "step": 26
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9599198590030308e-05,
+      "loss": 2.1292,
+      "step": 27
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9551024972069127e-05,
+      "loss": 1.9422,
+      "step": 28
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.950018434854704e-05,
+      "loss": 1.846,
+      "step": 29
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.944669091607919e-05,
+      "loss": 1.8679,
+      "step": 30
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9390559612044783e-05,
+      "loss": 1.7104,
+      "step": 31
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9331806110416027e-05,
+      "loss": 1.7278,
+      "step": 32
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9270446817381377e-05,
+      "loss": 2.0227,
+      "step": 33
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.920649886676429e-05,
+      "loss": 1.8487,
+      "step": 34
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.9139980115238827e-05,
+      "loss": 1.6051,
+      "step": 35
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.907090913734341e-05,
+      "loss": 1.6792,
+      "step": 36
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.899930522029408e-05,
+      "loss": 1.9176,
+      "step": 37
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.8925188358598815e-05,
+      "loss": 1.629,
+      "step": 38
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8848579248474286e-05,
+      "loss": 1.8579,
+      "step": 39
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8769499282066716e-05,
+      "loss": 1.6583,
+      "step": 40
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.8687970541478367e-05,
+      "loss": 1.7202,
+      "step": 41
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8604015792601395e-05,
+      "loss": 1.7408,
+      "step": 42
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.851765847876076e-05,
+      "loss": 1.7131,
+      "step": 43
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.842892271416797e-05,
+      "loss": 1.7969,
+      "step": 44
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.8337833277187472e-05,
+      "loss": 1.6165,
+      "step": 45
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.8244415603417603e-05,
+      "loss": 1.6652,
+      "step": 46
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.8148695778588034e-05,
+      "loss": 1.7009,
+      "step": 47
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.8050700531275632e-05,
+      "loss": 2.0433,
+      "step": 48
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.795045722544083e-05,
+      "loss": 1.577,
+      "step": 49
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.7847993852786612e-05,
+      "loss": 1.6598,
+      "step": 50
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 1.6191542148590088,
+      "eval_runtime": 10.8699,
+      "eval_samples_per_second": 2.576,
+      "eval_steps_per_second": 0.644,
+      "step": 50
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 198,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "total_flos": 1.2964555062981427e+17,
+  "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:d7fec19a554d0970f5e2dbe43273fbdb3e1b9cdfff23ccd1e725620293a85c95
+size 4920

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "NeverSleep/Nethena-20B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 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": "4.34.1",
+  "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
+}