012shin/qlora-koalpaca-polyglot-5.8b-QA

README.md

@@ -0,0 +1,58 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: beomi/KoAlpaca-Polyglot-5.8B
+model-index:
+- name: koalphaca_savepoint
+  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. -->
+
+# koalphaca_savepoint
+
+This model is a fine-tuned version of [beomi/KoAlpaca-Polyglot-5.8B](https://huggingface.co/beomi/KoAlpaca-Polyglot-5.8B) 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: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.11.2.dev0
+- Transformers 4.42.0.dev0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "beomi/KoAlpaca-Polyglot-5.8B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a86b9b72ba48a04c7a2a220d85a0e068044833d8b52072008cb9833706347c5
+size 14688200

runs/Jun03_07-21-51_deb33e102c39/events.out.tfevents.1717399324.deb33e102c39.993.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c4161beb299fae0b02f59abd995ef5bd7b96c3f2214b22f18cd788f391abcf9
+size 5790

runs/Jun03_07-23-22_deb33e102c39/events.out.tfevents.1717399414.deb33e102c39.993.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce0cae26e126218c499941bfc96f5655d737699eb10eed5789898410e9fab228
+size 194008

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:818cabfc6d38c1ed271f1477a2a657c812e4479fd56fe224b248f0e25aea9df4
+size 5176