Training in progress, step 8000, checkpoint

checkpoint-8000/README.md

@@ -0,0 +1,238 @@
+---
+library_name: peft
+base_model: EleutherAI/polyglot-ko-1.3b
+---
+
+# 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 0.6.2
+## 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 0.6.2

checkpoint-8000/adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "EleutherAI/polyglot-ko-1.3b",
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-8000/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46c871343b0ee32ff116726b64ef4cb00d17401d12186674fcf376ea62f6dbfa
+size 12600513

checkpoint-8000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07542489b4c58797bca6cf92054590a79b0fed8f0dceb2b4864b3ca346d754b3
+size 12589904

checkpoint-8000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e62a8538a552308fb07522b5b1261faf45305f7be4acc1874a3f9829ea6dd8fa
+size 25206149

checkpoint-8000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5268fd589d98b9d8915913e3e65371e74ce28ff3b16ffad24fb1f19b8a433c2f
+size 14639

checkpoint-8000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4846802d7a849598a10e234957776977c688638b56f184549a7155a68e9ab37b
+size 627

checkpoint-8000/special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|sep|>",
+    "<|acc|>",
+    "<|tel|>",
+    "<|rrn|>"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

checkpoint-8000/tokenizer_config.json

@@ -0,0 +1,72 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|unused0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|unused1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<|sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30000": {
+      "content": "<|acc|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30001": {
+      "content": "<|tel|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30002": {
+      "content": "<|rrn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|sep|>",
+    "<|acc|>",
+    "<|tel|>",
+    "<|rrn|>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-8000/trainer_state.json

@@ -0,0 +1,239 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 17.316017316017316,
+  "eval_steps": 1000,
+  "global_step": 8000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.65,
+      "learning_rate": 6.493506493506493e-07,
+      "loss": 2.3458,
+      "step": 300
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.2987012987012986e-06,
+      "loss": 2.3309,
+      "step": 600
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.9480519480519483e-06,
+      "loss": 2.2872,
+      "step": 900
+    },
+    {
+      "epoch": 2.16,
+      "eval_loss": 2.2653801441192627,
+      "eval_runtime": 40.5821,
+      "eval_samples_per_second": 64.166,
+      "eval_steps_per_second": 4.017,
+      "step": 1000
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 2.597402597402597e-06,
+      "loss": 2.2593,
+      "step": 1200
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 3.246753246753247e-06,
+      "loss": 2.2332,
+      "step": 1500
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 3.896103896103897e-06,
+      "loss": 2.1927,
+      "step": 1800
+    },
+    {
+      "epoch": 4.33,
+      "eval_loss": 2.181955575942993,
+      "eval_runtime": 40.5637,
+      "eval_samples_per_second": 64.195,
+      "eval_steps_per_second": 4.018,
+      "step": 2000
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 2.1735,
+      "step": 2100
+    },
+    {
+      "epoch": 5.19,
+      "learning_rate": 5.194805194805194e-06,
+      "loss": 2.1703,
+      "step": 2400
+    },
+    {
+      "epoch": 5.84,
+      "learning_rate": 5.844155844155844e-06,
+      "loss": 2.1335,
+      "step": 2700
+    },
+    {
+      "epoch": 6.49,
+      "learning_rate": 6.493506493506494e-06,
+      "loss": 2.1158,
+      "step": 3000
+    },
+    {
+      "epoch": 6.49,
+      "eval_loss": 2.119281530380249,
+      "eval_runtime": 40.6723,
+      "eval_samples_per_second": 64.024,
+      "eval_steps_per_second": 4.008,
+      "step": 3000
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 2.1031,
+      "step": 3300
+    },
+    {
+      "epoch": 7.79,
+      "learning_rate": 7.792207792207793e-06,
+      "loss": 2.0958,
+      "step": 3600
+    },
+    {
+      "epoch": 8.44,
+      "learning_rate": 8.441558441558442e-06,
+      "loss": 2.0816,
+      "step": 3900
+    },
+    {
+      "epoch": 8.66,
+      "eval_loss": 2.083141803741455,
+      "eval_runtime": 40.6586,
+      "eval_samples_per_second": 64.045,
+      "eval_steps_per_second": 4.009,
+      "step": 4000
+    },
+    {
+      "epoch": 9.09,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 2.07,
+      "step": 4200
+    },
+    {
+      "epoch": 9.74,
+      "learning_rate": 9.740259740259742e-06,
+      "loss": 2.0637,
+      "step": 4500
+    },
+    {
+      "epoch": 10.39,
+      "learning_rate": 9.96259251245514e-06,
+      "loss": 2.0616,
+      "step": 4800
+    },
+    {
+      "epoch": 10.82,
+      "eval_loss": 2.0597293376922607,
+      "eval_runtime": 40.7285,
+      "eval_samples_per_second": 63.936,
+      "eval_steps_per_second": 4.002,
+      "step": 5000
+    },
+    {
+      "epoch": 11.04,
+      "learning_rate": 9.736015051459551e-06,
+      "loss": 2.0349,
+      "step": 5100
+    },
+    {
+      "epoch": 11.69,
+      "learning_rate": 9.313027078004903e-06,
+      "loss": 2.0407,
+      "step": 5400
+    },
+    {
+      "epoch": 12.34,
+      "learning_rate": 8.71117061502135e-06,
+      "loss": 2.0326,
+      "step": 5700
+    },
+    {
+      "epoch": 12.99,
+      "learning_rate": 7.955405662643384e-06,
+      "loss": 2.0234,
+      "step": 6000
+    },
+    {
+      "epoch": 12.99,
+      "eval_loss": 2.0452144145965576,
+      "eval_runtime": 40.7967,
+      "eval_samples_per_second": 63.829,
+      "eval_steps_per_second": 3.995,
+      "step": 6000
+    },
+    {
+      "epoch": 13.64,
+      "learning_rate": 7.0770750650094335e-06,
+      "loss": 2.019,
+      "step": 6300
+    },
+    {
+      "epoch": 14.29,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 2.0186,
+      "step": 6600
+    },
+    {
+      "epoch": 14.94,
+      "learning_rate": 5.101992686957028e-06,
+      "loss": 2.0114,
+      "step": 6900
+    },
+    {
+      "epoch": 15.15,
+      "eval_loss": 2.0369863510131836,
+      "eval_runtime": 40.6659,
+      "eval_samples_per_second": 64.034,
+      "eval_steps_per_second": 4.008,
+      "step": 7000
+    },
+    {
+      "epoch": 15.58,
+      "learning_rate": 4.087150895803192e-06,
+      "loss": 2.0134,
+      "step": 7200
+    },
+    {
+      "epoch": 16.23,
+      "learning_rate": 3.110166492855468e-06,
+      "loss": 2.0014,
+      "step": 7500
+    },
+    {
+      "epoch": 16.88,
+      "learning_rate": 2.211556665065854e-06,
+      "loss": 2.011,
+      "step": 7800
+    },
+    {
+      "epoch": 17.32,
+      "eval_loss": 2.033980369567871,
+      "eval_runtime": 40.7311,
+      "eval_samples_per_second": 63.931,
+      "eval_steps_per_second": 4.002,
+      "step": 8000
+    }
+  ],
+  "logging_steps": 300,
+  "max_steps": 9240,
+  "num_train_epochs": 20,
+  "save_steps": 1000,
+  "total_flos": 5.568392565296333e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-8000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01cd81cf5bf64d274869694c75d5928fc39850c1ab5016c79515a4fb366079ee
+size 4155