End of training

README.md

@@ -0,0 +1,52 @@
+---
+base_model: elyza/Llama-3-ELYZA-JP-8B
+library_name: peft
+license: llama3
+tags:
+- generated_from_trainer
+model-index:
+- name: checkpoints
+  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. -->
+
+# checkpoints
+
+This model is a fine-tuned version of [elyza/Llama-3-ELYZA-JP-8B](https://huggingface.co/elyza/Llama-3-ELYZA-JP-8B) on an unknown 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: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 3
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.38.0
+- Pytorch 2.5.0+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "elyza/Llama-3-ELYZA-JP-8B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d323dd8662d386840d16526945909cc86099e8c6afb643012a2161b736cb20b5
+size 2269180144

runs/Nov01_11-45-23_8026237f0beb/events.out.tfevents.1730461534.8026237f0beb.1335.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a8128477e0ff5cef817cf2d09b677aa9f954b72c8f591a3f1e3fb6074455988
+size 5087

runs/Nov01_11-58-06_346ee69df94f/events.out.tfevents.1730462292.346ee69df94f.394.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ca29dba88cb36a7e0b5c6f140994f3d82b43257be35cfc3ee451e489a797d03
+size 5087

runs/Nov01_12-03-35_346ee69df94f/events.out.tfevents.1730462618.346ee69df94f.4547.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3ade689b36eb71ae71f44b2ec042e641c2c528b43d14bbf81a54b9952bb1caa
+size 88

runs/Nov01_12-04-46_346ee69df94f/events.out.tfevents.1730462688.346ee69df94f.5145.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c869b51adf160331aaef0f9e37299b0191a80a38f58567e6ff425778f642223e
+size 5087

runs/Nov01_12-04-46_346ee69df94f/events.out.tfevents.1730463100.346ee69df94f.5145.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9d4a6c17d1e5c3329da294f1d23541dbe58d36bd12cc6957c09bdfc753d7ff
+size 5087

runs/Nov01_12-24-50_af803120591d/events.out.tfevents.1730463894.af803120591d.705.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ccae775fbc5e5013583f534857159d79b7a976d21fb9852f524bb4715f26439
+size 5087

runs/Nov01_12-30-26_af803120591d/events.out.tfevents.1730464228.af803120591d.3728.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a952c383068723d384b7358dac64d845f1f0de5c5fae3e1069ccddd74bbf45b
+size 5085

runs/Nov01_12-39-09_af803120591d/events.out.tfevents.1730464751.af803120591d.6095.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53a0029da1d38098b8ec36ae218863b1620ebc94b3a172855695e9466131e045
+size 5085

runs/Nov01_12-52-16_150a91d0c167/events.out.tfevents.1730465539.150a91d0c167.2103.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b734f29f7e7c067e7a46508c8d7eea688457d0b372dc00b7ef8e010201635398
+size 5086

runs/Nov01_12-57-02_150a91d0c167/events.out.tfevents.1730465823.150a91d0c167.5646.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:985b642fef120ca5e9a66c8baeeaaa8150e5ee2068a0cf6ba44193a7f96a2a77
+size 88

runs/Nov01_12-59-09_150a91d0c167/events.out.tfevents.1730465951.150a91d0c167.6487.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f40a939ff44102a7be8cce00113ecd7f48871d21018faef5216c589108e4d9bc
+size 88

runs/Nov01_13-00-42_150a91d0c167/events.out.tfevents.1730466044.150a91d0c167.7128.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:362b1171590e72fa2f51a011ff5943f41736f4ae95938276508408b2a5f156df
+size 6741

runs/Nov01_14-44-42_150a91d0c167/events.out.tfevents.1730472409.150a91d0c167.32745.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e669fff208b008432d768ab24c33e853b0987a8774af0f616379b2f19b0c7ef
+size 12876

runs/Nov02_04-26-29_c4e7a60c812d/events.out.tfevents.1730521636.c4e7a60c812d.1718.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9244a2ed4d15bfe711e8fdd5b280478004fce7c9ad8d2bc77f3a2b0010ecdd52
+size 88

runs/Nov02_04-29-30_c4e7a60c812d/events.out.tfevents.1730521969.c4e7a60c812d.5304.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e47387f3a1c58ead55c5231b725f1e0985e17cf65c588fb6f434e16d0a3e5191
+size 5085

runs/Nov02_04-29-30_c4e7a60c812d/events.out.tfevents.1730522071.c4e7a60c812d.5304.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6655431426ecc3853fc1380f011302de258eeefe5f0f17e3b9e9cadd0a3c39f
+size 88

runs/Nov02_04-37-07_c4e7a60c812d/events.out.tfevents.1730522235.c4e7a60c812d.7682.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e43d29d56e038e72e961ec3bdee5dbc2b8fd17f4e9e7e17b65598dff7ac667e
+size 5292

runs/Nov02_05-00-58_c4e7a60c812d/events.out.tfevents.1730523659.c4e7a60c812d.13473.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea19eb3d498e85203781230307ef085f5f4a0efdcc3189384a0f6c47fc97f9ae
+size 8644

tmp-checkpoint-340/README.md

@@ -0,0 +1,202 @@
+---
+base_model: elyza/Llama-3-ELYZA-JP-8B
+library_name: peft
+---
+
+# 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]
+### Framework versions
+
+- PEFT 0.8.2

tmp-checkpoint-340/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "elyza/Llama-3-ELYZA-JP-8B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

tmp-checkpoint-340/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d323dd8662d386840d16526945909cc86099e8c6afb643012a2161b736cb20b5
+size 2269180144

tmp-checkpoint-340/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1e00c122f9a698d08d2fad9039766c6c6192ec651c9798684ee9a9b9db257f2
+size 1158803456

tmp-checkpoint-340/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edc9a0c8260b07ad924a04b4f453ff5ea01e0e53b379d36a3f62feb0cea9c0bd
+size 4920

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edc9a0c8260b07ad924a04b4f453ff5ea01e0e53b379d36a3f62feb0cea9c0bd
+size 4920