Upload folder using huggingface_hub

README.md

@@ -0,0 +1,76 @@
+---
+license: llama2
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: tavtav/Rose-20B
+model-index:
+- name: qlora-out
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+# qlora-out
+
+This model is a fine-tuned version of [tavtav/Rose-20B](https://huggingface.co/tavtav/Rose-20B) on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.36.0.dev0
+- Pytorch 2.0.1+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.0

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "tavtav/Rose-20B",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_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:e3d349e740c00b2991d8f849e35d1e842d39ecf0b77bebedae79dc7ccfdc767d
+size 194331549

added_tokens.json

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

checkpoint-108/README.md

@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: tavtav/Rose-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: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.0

checkpoint-108/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "tavtav/Rose-20B",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-108/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3d088d020c0c56a8eb4ce6a29a6506de0476cafa2f524da4f419a9df7bf8473
+size 194135104

checkpoint-108/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:094e5b80aba18fe361c99dd451857e151493b6ff68663ca4b8aad4313c72d51b
+size 194285701

checkpoint-108/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad5c7308f5d160ac76e2bf632a71aca9b0fff0cc79917875d57f999108891517
+size 14575

checkpoint-108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c4b310a6a2b489fb2972010bde98793e0a96d0e048f1e2cec43af9f9cffe06f
+size 627

checkpoint-108/trainer_state.json

@@ -0,0 +1,669 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0334928229665072,
+  "eval_steps": 500,
+  "global_step": 108,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2e-05,
+      "loss": 2.3634,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4e-05,
+      "loss": 2.4605,
+      "step": 2
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6e-05,
+      "loss": 2.3783,
+      "step": 3
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8e-05,
+      "loss": 2.5611,
+      "step": 4
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001,
+      "loss": 2.525,
+      "step": 5
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00012,
+      "loss": 2.4104,
+      "step": 6
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00014,
+      "loss": 2.3589,
+      "step": 7
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00016,
+      "loss": 2.4133,
+      "step": 8
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00018,
+      "loss": 2.1582,
+      "step": 9
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0002,
+      "loss": 2.1394,
+      "step": 10
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019998741276738754,
+      "loss": 2.1466,
+      "step": 11
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019994965423831854,
+      "loss": 2.0672,
+      "step": 12
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0001998867339183008,
+      "loss": 2.1323,
+      "step": 13
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00019979866764718843,
+      "loss": 2.0887,
+      "step": 14
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00019968547759519425,
+      "loss": 2.1057,
+      "step": 15
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019954719225730847,
+      "loss": 2.0863,
+      "step": 16
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019938384644612543,
+      "loss": 2.09,
+      "step": 17
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019919548128307954,
+      "loss": 2.0731,
+      "step": 18
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0001989821441880933,
+      "loss": 2.1503,
+      "step": 19
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00019874388886763944,
+      "loss": 1.9755,
+      "step": 20
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00019848077530122083,
+      "loss": 2.117,
+      "step": 21
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00019819286972627066,
+      "loss": 1.9935,
+      "step": 22
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00019788024462147788,
+      "loss": 2.0685,
+      "step": 23
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00019754297868854073,
+      "loss": 2.0086,
+      "step": 24
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019718115683235417,
+      "loss": 2.0013,
+      "step": 25
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00019679487013963564,
+      "loss": 2.0066,
+      "step": 26
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00019638421585599423,
+      "loss": 1.9823,
+      "step": 27
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00019594929736144976,
+      "loss": 2.0394,
+      "step": 28
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0001954902241444074,
+      "loss": 2.0804,
+      "step": 29
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00019500711177409454,
+      "loss": 1.997,
+      "step": 30
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00019450008187146684,
+      "loss": 2.0794,
+      "step": 31
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 1.9769,
+      "step": 32
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00019341478602651069,
+      "loss": 1.9643,
+      "step": 33
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00019283679330160726,
+      "loss": 2.041,
+      "step": 34
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00019223542941045817,
+      "loss": 1.9873,
+      "step": 35
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00019161084574320696,
+      "loss": 2.0358,
+      "step": 36
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00019096319953545185,
+      "loss": 2.021,
+      "step": 37
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00019029265382866214,
+      "loss": 2.0764,
+      "step": 38
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00018959937742913359,
+      "loss": 2.1639,
+      "step": 39
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00018888354486549237,
+      "loss": 2.0892,
+      "step": 40
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00018814533634475822,
+      "loss": 1.9749,
+      "step": 41
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00018738493770697852,
+      "loss": 2.0521,
+      "step": 42
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 2.0751,
+      "step": 43
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00018579834132349772,
+      "loss": 2.0852,
+      "step": 44
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00018497254299495146,
+      "loss": 1.9871,
+      "step": 45
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00018412535328311814,
+      "loss": 1.9199,
+      "step": 46
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00018325698546347715,
+      "loss": 1.9627,
+      "step": 47
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0001823676581429833,
+      "loss": 2.0465,
+      "step": 48
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00018145759520503358,
+      "loss": 2.0033,
+      "step": 49
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00018052702575310588,
+      "loss": 1.8835,
+      "step": 50
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00017957618405308324,
+      "loss": 1.9823,
+      "step": 51
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00017860530947427875,
+      "loss": 2.0887,
+      "step": 52
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0001776146464291757,
+      "loss": 2.0936,
+      "step": 53
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 2.0576,
+      "step": 54
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00017557495743542585,
+      "loss": 1.8788,
+      "step": 55
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0001745264449675755,
+      "loss": 2.0452,
+      "step": 56
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00017345917086575332,
+      "loss": 2.0411,
+      "step": 57
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00017237340381050703,
+      "loss": 2.0834,
+      "step": 58
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00017126941713788632,
+      "loss": 2.113,
+      "step": 59
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00017014748877063214,
+      "loss": 2.0797,
+      "step": 60
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00016900790114821122,
+      "loss": 2.0783,
+      "step": 61
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00016785094115571322,
+      "loss": 1.9576,
+      "step": 62
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00016667690005162916,
+      "loss": 1.9651,
+      "step": 63
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00016548607339452853,
+      "loss": 1.9927,
+      "step": 64
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00016427876096865394,
+      "loss": 2.0967,
+      "step": 65
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00016305526670845226,
+      "loss": 2.0661,
+      "step": 66
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00016181589862206052,
+      "loss": 1.9413,
+      "step": 67
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00016056096871376667,
+      "loss": 1.8223,
+      "step": 68
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00015929079290546408,
+      "loss": 2.0162,
+      "step": 69
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00015800569095711982,
+      "loss": 1.9682,
+      "step": 70
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00015670598638627706,
+      "loss": 1.8836,
+      "step": 71
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00015539200638661104,
+      "loss": 1.9973,
+      "step": 72
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00015406408174555976,
+      "loss": 2.1492,
+      "step": 73
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00015272254676105025,
+      "loss": 1.9856,
+      "step": 74
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00015136773915734066,
+      "loss": 1.9407,
+      "step": 75
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 2.0559,
+      "step": 76
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00014861967361004687,
+      "loss": 1.9553,
+      "step": 77
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0001472271074772683,
+      "loss": 1.996,
+      "step": 78
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00014582265217274104,
+      "loss": 2.2306,
+      "step": 79
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00014440666126057744,
+      "loss": 2.0002,
+      "step": 80
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00014297949120891718,
+      "loss": 2.068,
+      "step": 81
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00014154150130018866,
+      "loss": 2.0615,
+      "step": 82
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00014009305354066137,
+      "loss": 2.0083,
+      "step": 83
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00013863451256931287,
+      "loss": 1.9979,
+      "step": 84
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00013716624556603274,
+      "loss": 1.8525,
+      "step": 85
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00013568862215918717,
+      "loss": 2.045,
+      "step": 86
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 1.9144,
+      "step": 87
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00013270679633174218,
+      "loss": 1.9353,
+      "step": 88
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0001312033445698487,
+      "loss": 2.1257,
+      "step": 89
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0001296920375328275,
+      "loss": 1.906,
+      "step": 90
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00012817325568414297,
+      "loss": 1.9963,
+      "step": 91
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00012664738136900348,
+      "loss": 2.0734,
+      "step": 92
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0001251147987181079,
+      "loss": 2.0182,
+      "step": 93
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00012357589355094275,
+      "loss": 1.9574,
+      "step": 94
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00012203105327865407,
+      "loss": 2.1562,
+      "step": 95
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00012048066680651908,
+      "loss": 2.082,
+      "step": 96
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00011892512443604102,
+      "loss": 1.9546,
+      "step": 97
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 2.0957,
+      "step": 98
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.000115800139597335,
+      "loss": 1.9348,
+      "step": 99
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00011423148382732853,
+      "loss": 2.0772,
+      "step": 100
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00011265924535737493,
+      "loss": 2.0298,
+      "step": 101
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00011108381999010111,
+      "loss": 2.0272,
+      "step": 102
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00010950560433041826,
+      "loss": 2.0293,
+      "step": 103
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00010792499568567884,
+      "loss": 1.8576,
+      "step": 104
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00010634239196565646,
+      "loss": 1.9792,
+      "step": 105
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00010475819158237425,
+      "loss": 1.8629,
+      "step": 106
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00010317279334980678,
+      "loss": 2.0062,
+      "step": 107
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00010158659638348081,
+      "loss": 1.937,
+      "step": 108
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 208,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 4.245474393540526e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2fe1f38496165c805c67e7b363ce3147bcdfdf536b5617c1b660339807243a9
+size 4731

checkpoint-208/README.md

@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: tavtav/Rose-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: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.0

checkpoint-208/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "tavtav/Rose-20B",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-208/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:356f22ceb28d497b07072a35a9bea3f8ab9bd84dc872900cbb7550772c4bbfbd
+size 194135104

checkpoint-208/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1146121dc75284e66edf3da08723306f4669ef82fd9d5a8d2108c910282d1ea
+size 194285701

checkpoint-208/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a533e6616a07aa5ca07629e3728bb909706f32c42b413ab03e02c5a629c28d9d
+size 14575

checkpoint-208/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06d271c3262b82453e3bccf37c67f466271b9e2ae835d84ed5f7a1f0b81d7a88
+size 627

checkpoint-208/trainer_state.json

@@ -0,0 +1,1269 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9497607655502391,
+  "eval_steps": 500,
+  "global_step": 208,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2e-05,
+      "loss": 2.3634,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4e-05,
+      "loss": 2.4605,
+      "step": 2
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6e-05,
+      "loss": 2.3783,
+      "step": 3
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8e-05,
+      "loss": 2.5611,
+      "step": 4
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001,
+      "loss": 2.525,
+      "step": 5
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00012,
+      "loss": 2.4104,
+      "step": 6
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00014,
+      "loss": 2.3589,
+      "step": 7
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00016,
+      "loss": 2.4133,
+      "step": 8
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00018,
+      "loss": 2.1582,
+      "step": 9
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0002,
+      "loss": 2.1394,
+      "step": 10
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019998741276738754,
+      "loss": 2.1466,
+      "step": 11
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019994965423831854,
+      "loss": 2.0672,
+      "step": 12
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0001998867339183008,
+      "loss": 2.1323,
+      "step": 13
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00019979866764718843,
+      "loss": 2.0887,
+      "step": 14
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00019968547759519425,
+      "loss": 2.1057,
+      "step": 15
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019954719225730847,
+      "loss": 2.0863,
+      "step": 16
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019938384644612543,
+      "loss": 2.09,
+      "step": 17
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019919548128307954,
+      "loss": 2.0731,
+      "step": 18
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0001989821441880933,
+      "loss": 2.1503,
+      "step": 19
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00019874388886763944,
+      "loss": 1.9755,
+      "step": 20
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00019848077530122083,
+      "loss": 2.117,
+      "step": 21
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00019819286972627066,
+      "loss": 1.9935,
+      "step": 22
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00019788024462147788,
+      "loss": 2.0685,
+      "step": 23
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00019754297868854073,
+      "loss": 2.0086,
+      "step": 24
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019718115683235417,
+      "loss": 2.0013,
+      "step": 25
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00019679487013963564,
+      "loss": 2.0066,
+      "step": 26
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00019638421585599423,
+      "loss": 1.9823,
+      "step": 27
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00019594929736144976,
+      "loss": 2.0394,
+      "step": 28
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0001954902241444074,
+      "loss": 2.0804,
+      "step": 29
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00019500711177409454,
+      "loss": 1.997,
+      "step": 30
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00019450008187146684,
+      "loss": 2.0794,
+      "step": 31
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 1.9769,
+      "step": 32
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00019341478602651069,
+      "loss": 1.9643,
+      "step": 33
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00019283679330160726,
+      "loss": 2.041,
+      "step": 34
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00019223542941045817,
+      "loss": 1.9873,
+      "step": 35
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00019161084574320696,
+      "loss": 2.0358,
+      "step": 36
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00019096319953545185,
+      "loss": 2.021,
+      "step": 37
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00019029265382866214,
+      "loss": 2.0764,
+      "step": 38
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00018959937742913359,
+      "loss": 2.1639,
+      "step": 39
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00018888354486549237,
+      "loss": 2.0892,
+      "step": 40
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00018814533634475822,
+      "loss": 1.9749,
+      "step": 41
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00018738493770697852,
+      "loss": 2.0521,
+      "step": 42
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 2.0751,
+      "step": 43
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00018579834132349772,
+      "loss": 2.0852,
+      "step": 44
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00018497254299495146,
+      "loss": 1.9871,
+      "step": 45
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00018412535328311814,
+      "loss": 1.9199,
+      "step": 46
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00018325698546347715,
+      "loss": 1.9627,
+      "step": 47
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0001823676581429833,
+      "loss": 2.0465,
+      "step": 48
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00018145759520503358,
+      "loss": 2.0033,
+      "step": 49
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00018052702575310588,
+      "loss": 1.8835,
+      "step": 50
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00017957618405308324,
+      "loss": 1.9823,
+      "step": 51
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00017860530947427875,
+      "loss": 2.0887,
+      "step": 52
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0001776146464291757,
+      "loss": 2.0936,
+      "step": 53
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 2.0576,
+      "step": 54
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00017557495743542585,
+      "loss": 1.8788,
+      "step": 55
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0001745264449675755,
+      "loss": 2.0452,
+      "step": 56
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00017345917086575332,
+      "loss": 2.0411,
+      "step": 57
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00017237340381050703,
+      "loss": 2.0834,
+      "step": 58
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00017126941713788632,
+      "loss": 2.113,
+      "step": 59
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00017014748877063214,
+      "loss": 2.0797,
+      "step": 60
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00016900790114821122,
+      "loss": 2.0783,
+      "step": 61
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00016785094115571322,
+      "loss": 1.9576,
+      "step": 62
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00016667690005162916,
+      "loss": 1.9651,
+      "step": 63
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00016548607339452853,
+      "loss": 1.9927,
+      "step": 64
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00016427876096865394,
+      "loss": 2.0967,
+      "step": 65
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00016305526670845226,
+      "loss": 2.0661,
+      "step": 66
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00016181589862206052,
+      "loss": 1.9413,
+      "step": 67
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00016056096871376667,
+      "loss": 1.8223,
+      "step": 68
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00015929079290546408,
+      "loss": 2.0162,
+      "step": 69
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00015800569095711982,
+      "loss": 1.9682,
+      "step": 70
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00015670598638627706,
+      "loss": 1.8836,
+      "step": 71
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00015539200638661104,
+      "loss": 1.9973,
+      "step": 72
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00015406408174555976,
+      "loss": 2.1492,
+      "step": 73
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00015272254676105025,
+      "loss": 1.9856,
+      "step": 74
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00015136773915734066,
+      "loss": 1.9407,
+      "step": 75
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 2.0559,
+      "step": 76
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00014861967361004687,
+      "loss": 1.9553,
+      "step": 77
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0001472271074772683,
+      "loss": 1.996,
+      "step": 78
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00014582265217274104,
+      "loss": 2.2306,
+      "step": 79
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00014440666126057744,
+      "loss": 2.0002,
+      "step": 80
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00014297949120891718,
+      "loss": 2.068,
+      "step": 81
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00014154150130018866,
+      "loss": 2.0615,
+      "step": 82
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00014009305354066137,
+      "loss": 2.0083,
+      "step": 83
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00013863451256931287,
+      "loss": 1.9979,
+      "step": 84
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00013716624556603274,
+      "loss": 1.8525,
+      "step": 85
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00013568862215918717,
+      "loss": 2.045,
+      "step": 86
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 1.9144,
+      "step": 87
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00013270679633174218,
+      "loss": 1.9353,
+      "step": 88
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0001312033445698487,
+      "loss": 2.1257,
+      "step": 89
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0001296920375328275,
+      "loss": 1.906,
+      "step": 90
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00012817325568414297,
+      "loss": 1.9963,
+      "step": 91
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00012664738136900348,
+      "loss": 2.0734,
+      "step": 92
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0001251147987181079,
+      "loss": 2.0182,
+      "step": 93
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00012357589355094275,
+      "loss": 1.9574,
+      "step": 94
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00012203105327865407,
+      "loss": 2.1562,
+      "step": 95
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00012048066680651908,
+      "loss": 2.082,
+      "step": 96
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00011892512443604102,
+      "loss": 1.9546,
+      "step": 97
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 2.0957,
+      "step": 98
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.000115800139597335,
+      "loss": 1.9348,
+      "step": 99
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00011423148382732853,
+      "loss": 2.0772,
+      "step": 100
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00011265924535737493,
+      "loss": 2.0298,
+      "step": 101
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00011108381999010111,
+      "loss": 2.0272,
+      "step": 102
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00010950560433041826,
+      "loss": 2.0293,
+      "step": 103
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00010792499568567884,
+      "loss": 1.8576,
+      "step": 104
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00010634239196565646,
+      "loss": 1.9792,
+      "step": 105
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00010475819158237425,
+      "loss": 1.8629,
+      "step": 106
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00010317279334980678,
+      "loss": 2.0062,
+      "step": 107
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00010158659638348081,
+      "loss": 1.937,
+      "step": 108
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0001,
+      "loss": 2.0037,
+      "step": 109
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 9.84134036165192e-05,
+      "loss": 1.996,
+      "step": 110
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 9.682720665019325e-05,
+      "loss": 1.9546,
+      "step": 111
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 9.524180841762577e-05,
+      "loss": 1.7773,
+      "step": 112
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 9.365760803434355e-05,
+      "loss": 1.9081,
+      "step": 113
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 9.207500431432115e-05,
+      "loss": 1.9541,
+      "step": 114
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 9.049439566958175e-05,
+      "loss": 1.8794,
+      "step": 115
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 8.891618000989891e-05,
+      "loss": 1.8764,
+      "step": 116
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 8.734075464262507e-05,
+      "loss": 1.9087,
+      "step": 117
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 8.57685161726715e-05,
+      "loss": 1.9862,
+      "step": 118
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 8.4199860402665e-05,
+      "loss": 2.0019,
+      "step": 119
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 1.9839,
+      "step": 120
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.107487556395901e-05,
+      "loss": 1.8805,
+      "step": 121
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 7.951933319348095e-05,
+      "loss": 1.9964,
+      "step": 122
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 7.796894672134594e-05,
+      "loss": 1.9832,
+      "step": 123
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 7.642410644905726e-05,
+      "loss": 1.8678,
+      "step": 124
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 7.488520128189209e-05,
+      "loss": 1.9307,
+      "step": 125
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 7.335261863099651e-05,
+      "loss": 1.9972,
+      "step": 126
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 7.182674431585704e-05,
+      "loss": 1.9596,
+      "step": 127
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 7.030796246717255e-05,
+      "loss": 1.8535,
+      "step": 128
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 6.87966554301513e-05,
+      "loss": 1.9233,
+      "step": 129
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 6.729320366825784e-05,
+      "loss": 1.9672,
+      "step": 130
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 6.579798566743314e-05,
+      "loss": 1.9245,
+      "step": 131
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.431137784081282e-05,
+      "loss": 1.9376,
+      "step": 132
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 6.283375443396726e-05,
+      "loss": 1.957,
+      "step": 133
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.136548743068713e-05,
+      "loss": 1.9098,
+      "step": 134
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 5.9906946459338656e-05,
+      "loss": 1.8468,
+      "step": 135
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 5.845849869981137e-05,
+      "loss": 1.9754,
+      "step": 136
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 5.702050879108284e-05,
+      "loss": 2.0446,
+      "step": 137
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 5.559333873942259e-05,
+      "loss": 1.959,
+      "step": 138
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 5.417734782725896e-05,
+      "loss": 2.0479,
+      "step": 139
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.277289252273174e-05,
+      "loss": 2.0104,
+      "step": 140
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.138032638995315e-05,
+      "loss": 1.8287,
+      "step": 141
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 2.0405,
+      "step": 142
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 4.8632260842659393e-05,
+      "loss": 1.7512,
+      "step": 143
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 4.727745323894976e-05,
+      "loss": 1.9735,
+      "step": 144
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.593591825444028e-05,
+      "loss": 1.9186,
+      "step": 145
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.4607993613388976e-05,
+      "loss": 1.9525,
+      "step": 146
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.329401361372294e-05,
+      "loss": 1.9657,
+      "step": 147
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.19943090428802e-05,
+      "loss": 1.884,
+      "step": 148
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.070920709453597e-05,
+      "loss": 1.8609,
+      "step": 149
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 3.943903128623335e-05,
+      "loss": 1.9839,
+      "step": 150
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 3.8184101377939476e-05,
+      "loss": 2.133,
+      "step": 151
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 3.694473329154778e-05,
+      "loss": 1.9601,
+      "step": 152
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 1.9665,
+      "step": 153
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.45139266054715e-05,
+      "loss": 1.9298,
+      "step": 154
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.332309994837085e-05,
+      "loss": 1.9882,
+      "step": 155
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.21490588442868e-05,
+      "loss": 1.9381,
+      "step": 156
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 3.099209885178882e-05,
+      "loss": 1.9314,
+      "step": 157
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 2.9852511229367865e-05,
+      "loss": 2.0151,
+      "step": 158
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 2.8730582862113742e-05,
+      "loss": 1.8828,
+      "step": 159
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 2.7626596189492983e-05,
+      "loss": 1.9468,
+      "step": 160
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.654082913424668e-05,
+      "loss": 1.9597,
+      "step": 161
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 2.5473555032424533e-05,
+      "loss": 2.0673,
+      "step": 162
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.4425042564574184e-05,
+      "loss": 1.8841,
+      "step": 163
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 1.8973,
+      "step": 164
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2.2385353570824308e-05,
+      "loss": 2.0362,
+      "step": 165
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.139469052572127e-05,
+      "loss": 1.8493,
+      "step": 166
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.042381594691678e-05,
+      "loss": 1.9594,
+      "step": 167
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1.947297424689414e-05,
+      "loss": 1.8966,
+      "step": 168
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1.854240479496643e-05,
+      "loss": 1.881,
+      "step": 169
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1.763234185701673e-05,
+      "loss": 1.9359,
+      "step": 170
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.6743014536522873e-05,
+      "loss": 2.0055,
+      "step": 171
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.587464671688187e-05,
+      "loss": 1.8821,
+      "step": 172
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.5027457005048573e-05,
+      "loss": 1.7915,
+      "step": 173
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.4201658676502294e-05,
+      "loss": 1.9249,
+      "step": 174
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.9576,
+      "step": 175
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.2615062293021507e-05,
+      "loss": 1.9853,
+      "step": 176
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.1854663655241805e-05,
+      "loss": 1.9205,
+      "step": 177
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.1116455134507664e-05,
+      "loss": 1.8719,
+      "step": 178
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.0400622570866425e-05,
+      "loss": 1.9103,
+      "step": 179
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 9.707346171337894e-06,
+      "loss": 1.8143,
+      "step": 180
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 9.036800464548157e-06,
+      "loss": 2.0218,
+      "step": 181
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8.38915425679304e-06,
+      "loss": 2.02,
+      "step": 182
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 7.764570589541875e-06,
+      "loss": 2.0398,
+      "step": 183
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 7.163206698392744e-06,
+      "loss": 1.8979,
+      "step": 184
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 6.585213973489335e-06,
+      "loss": 1.9078,
+      "step": 185
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 1.9421,
+      "step": 186
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 5.499918128533155e-06,
+      "loss": 2.0254,
+      "step": 187
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 4.992888225905468e-06,
+      "loss": 2.0184,
+      "step": 188
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 4.509775855592613e-06,
+      "loss": 2.2174,
+      "step": 189
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 4.050702638550275e-06,
+      "loss": 2.0188,
+      "step": 190
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 3.615784144005796e-06,
+      "loss": 2.0355,
+      "step": 191
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 3.2051298603643753e-06,
+      "loss": 1.8947,
+      "step": 192
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 2.818843167645835e-06,
+      "loss": 1.952,
+      "step": 193
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 2.4570213114592954e-06,
+      "loss": 1.9703,
+      "step": 194
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 2.119755378522137e-06,
+      "loss": 1.9051,
+      "step": 195
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.8071302737293295e-06,
+      "loss": 1.9829,
+      "step": 196
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 2.1096,
+      "step": 197
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 1.2561111323605712e-06,
+      "loss": 1.9162,
+      "step": 198
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.0178558119067315e-06,
+      "loss": 1.944,
+      "step": 199
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 8.04518716920466e-07,
+      "loss": 1.9719,
+      "step": 200
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 6.161535538745878e-07,
+      "loss": 1.8808,
+      "step": 201
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 4.5280774269154115e-07,
+      "loss": 1.9213,
+      "step": 202
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.145224048057727e-07,
+      "loss": 1.9598,
+      "step": 203
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2.0133235281156736e-07,
+      "loss": 1.9825,
+      "step": 204
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.1326608169920372e-07,
+      "loss": 1.9515,
+      "step": 205
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 5.0345761681491746e-08,
+      "loss": 1.7554,
+      "step": 206
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.2587232612493172e-08,
+      "loss": 1.8226,
+      "step": 207
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.0,
+      "loss": 1.9169,
+      "step": 208
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 208,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 8.124538453921628e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-208/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2fe1f38496165c805c67e7b363ce3147bcdfdf536b5617c1b660339807243a9
+size 4731

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "tavtav/Rose-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": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32001
+}

runs/Dec11_06-12-11_92e131aa371d/events.out.tfevents.1702275131.92e131aa371d.683.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b49e20db18772e37c6dd235f803a297da79c226c1099045e2fe7cac17e3525da
+size 6030

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
+}