Upload 8 files

README.md

@@ -1,3 +1,219 @@
 ---
-license: apache-2.0
+library_name: peft
+base_model: EleutherAI/polyglot-ko-12.8b
 ---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0

adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "EleutherAI/polyglot-ko-12.8b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "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": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3997d823be258b16cd25b90f386e04647ebb4f47d42a24bf43f7b692d59e9e4
+size 26243937

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51380c6cbe58cfdfb83f64fd36aaef2865627b047232526969755fd17274dd73
+size 13224133

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9abceee9b0ad6256e82e821e6d9e1eb5215aca37d459a8cfb621db7f807dd5a4
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffa84e40719b997939d68759cd6081e20cd194a4249148874782150e77884095
+size 627

trainer_state.json

@@ -0,0 +1,619 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.246376811594203,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 3.3296,
+      "step": 10
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000196,
+      "loss": 2.5227,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.000194,
+      "loss": 2.0348,
+      "step": 30
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.000192,
+      "loss": 1.9388,
+      "step": 40
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00019,
+      "loss": 1.9197,
+      "step": 50
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.000188,
+      "loss": 1.814,
+      "step": 60
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00018600000000000002,
+      "loss": 1.5649,
+      "step": 70
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 1.6691,
+      "step": 80
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.000182,
+      "loss": 1.6885,
+      "step": 90
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00018,
+      "loss": 1.6748,
+      "step": 100
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 1.6405,
+      "step": 110
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 1.5524,
+      "step": 120
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.000174,
+      "loss": 1.374,
+      "step": 130
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.000172,
+      "loss": 1.4287,
+      "step": 140
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00017,
+      "loss": 1.228,
+      "step": 150
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.000168,
+      "loss": 1.3442,
+      "step": 160
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.000166,
+      "loss": 1.3386,
+      "step": 170
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.000164,
+      "loss": 1.2911,
+      "step": 180
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.000162,
+      "loss": 1.2203,
+      "step": 190
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00016,
+      "loss": 1.1671,
+      "step": 200
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 1.4117,
+      "step": 210
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 1.1522,
+      "step": 220
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.000154,
+      "loss": 1.3722,
+      "step": 230
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.000152,
+      "loss": 1.3268,
+      "step": 240
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.1648,
+      "step": 250
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.000148,
+      "loss": 1.2187,
+      "step": 260
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.000146,
+      "loss": 1.2501,
+      "step": 270
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 0.000144,
+      "loss": 1.0928,
+      "step": 280
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 0.000142,
+      "loss": 0.8553,
+      "step": 290
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 0.00014,
+      "loss": 0.8745,
+      "step": 300
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 0.000138,
+      "loss": 0.9068,
+      "step": 310
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 0.9783,
+      "step": 320
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 0.000134,
+      "loss": 0.9185,
+      "step": 330
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 0.000132,
+      "loss": 0.929,
+      "step": 340
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 0.9308,
+      "step": 350
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 0.929,
+      "step": 360
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 0.000126,
+      "loss": 1.0682,
+      "step": 370
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 0.000124,
+      "loss": 0.9615,
+      "step": 380
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 0.000122,
+      "loss": 0.9984,
+      "step": 390
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 0.00012,
+      "loss": 0.9162,
+      "step": 400
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 0.000118,
+      "loss": 0.7737,
+      "step": 410
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 0.000116,
+      "loss": 0.8563,
+      "step": 420
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 0.5843,
+      "step": 430
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 0.6378,
+      "step": 440
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 0.5818,
+      "step": 450
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 0.6841,
+      "step": 460
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 0.00010600000000000002,
+      "loss": 0.6338,
+      "step": 470
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 0.6083,
+      "step": 480
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 0.00010200000000000001,
+      "loss": 0.6408,
+      "step": 490
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 0.0001,
+      "loss": 0.677,
+      "step": 500
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 9.8e-05,
+      "loss": 0.6878,
+      "step": 510
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 9.6e-05,
+      "loss": 0.5942,
+      "step": 520
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 9.4e-05,
+      "loss": 0.5855,
+      "step": 530
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 0.6314,
+      "step": 540
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 9e-05,
+      "loss": 0.6157,
+      "step": 550
+    },
+    {
+      "epoch": 4.06,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 0.399,
+      "step": 560
+    },
+    {
+      "epoch": 4.13,
+      "learning_rate": 8.6e-05,
+      "loss": 0.3511,
+      "step": 570
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 8.4e-05,
+      "loss": 0.4271,
+      "step": 580
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 8.2e-05,
+      "loss": 0.4539,
+      "step": 590
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 8e-05,
+      "loss": 0.3656,
+      "step": 600
+    },
+    {
+      "epoch": 4.42,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 0.4041,
+      "step": 610
+    },
+    {
+      "epoch": 4.49,
+      "learning_rate": 7.6e-05,
+      "loss": 0.4036,
+      "step": 620
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 7.4e-05,
+      "loss": 0.3964,
+      "step": 630
+    },
+    {
+      "epoch": 4.64,
+      "learning_rate": 7.2e-05,
+      "loss": 0.4016,
+      "step": 640
+    },
+    {
+      "epoch": 4.71,
+      "learning_rate": 7e-05,
+      "loss": 0.3499,
+      "step": 650
+    },
+    {
+      "epoch": 4.78,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 0.4193,
+      "step": 660
+    },
+    {
+      "epoch": 4.86,
+      "learning_rate": 6.6e-05,
+      "loss": 0.3946,
+      "step": 670
+    },
+    {
+      "epoch": 4.93,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.4058,
+      "step": 680
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 6.2e-05,
+      "loss": 0.4132,
+      "step": 690
+    },
+    {
+      "epoch": 5.07,
+      "learning_rate": 6e-05,
+      "loss": 0.2782,
+      "step": 700
+    },
+    {
+      "epoch": 5.14,
+      "learning_rate": 5.8e-05,
+      "loss": 0.2496,
+      "step": 710
+    },
+    {
+      "epoch": 5.22,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.259,
+      "step": 720
+    },
+    {
+      "epoch": 5.29,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 0.2572,
+      "step": 730
+    },
+    {
+      "epoch": 5.36,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 0.2885,
+      "step": 740
+    },
+    {
+      "epoch": 5.43,
+      "learning_rate": 5e-05,
+      "loss": 0.2383,
+      "step": 750
+    },
+    {
+      "epoch": 5.51,
+      "learning_rate": 4.8e-05,
+      "loss": 0.2976,
+      "step": 760
+    },
+    {
+      "epoch": 5.58,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.287,
+      "step": 770
+    },
+    {
+      "epoch": 5.65,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.2737,
+      "step": 780
+    },
+    {
+      "epoch": 5.72,
+      "learning_rate": 4.2e-05,
+      "loss": 0.2412,
+      "step": 790
+    },
+    {
+      "epoch": 5.8,
+      "learning_rate": 4e-05,
+      "loss": 0.2736,
+      "step": 800
+    },
+    {
+      "epoch": 5.87,
+      "learning_rate": 3.8e-05,
+      "loss": 0.278,
+      "step": 810
+    },
+    {
+      "epoch": 5.94,
+      "learning_rate": 3.6e-05,
+      "loss": 0.2871,
+      "step": 820
+    },
+    {
+      "epoch": 6.01,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 0.243,
+      "step": 830
+    },
+    {
+      "epoch": 6.09,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.1926,
+      "step": 840
+    },
+    {
+      "epoch": 6.16,
+      "learning_rate": 3e-05,
+      "loss": 0.2136,
+      "step": 850
+    },
+    {
+      "epoch": 6.23,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.2247,
+      "step": 860
+    },
+    {
+      "epoch": 6.3,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 0.2212,
+      "step": 870
+    },
+    {
+      "epoch": 6.38,
+      "learning_rate": 2.4e-05,
+      "loss": 0.201,
+      "step": 880
+    },
+    {
+      "epoch": 6.45,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 0.2074,
+      "step": 890
+    },
+    {
+      "epoch": 6.52,
+      "learning_rate": 2e-05,
+      "loss": 0.2087,
+      "step": 900
+    },
+    {
+      "epoch": 6.59,
+      "learning_rate": 1.8e-05,
+      "loss": 0.1979,
+      "step": 910
+    },
+    {
+      "epoch": 6.67,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.2152,
+      "step": 920
+    },
+    {
+      "epoch": 6.74,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 0.2207,
+      "step": 930
+    },
+    {
+      "epoch": 6.81,
+      "learning_rate": 1.2e-05,
+      "loss": 0.2088,
+      "step": 940
+    },
+    {
+      "epoch": 6.88,
+      "learning_rate": 1e-05,
+      "loss": 0.2059,
+      "step": 950
+    },
+    {
+      "epoch": 6.96,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.2092,
+      "step": 960
+    },
+    {
+      "epoch": 7.03,
+      "learning_rate": 6e-06,
+      "loss": 0.1882,
+      "step": 970
+    },
+    {
+      "epoch": 7.1,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.1814,
+      "step": 980
+    },
+    {
+      "epoch": 7.17,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.16,
+      "step": 990
+    },
+    {
+      "epoch": 7.25,
+      "learning_rate": 0.0,
+      "loss": 0.1653,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1000,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 9570470597959680.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cda49281b7cdb43e029edb7bd0a1c12abf57068f025285352d591ab4bf99ea6d
+size 4027