myewon/finetuning_result

README.md

@@ -0,0 +1,56 @@
+---
+base_model: NousResearch/Llama-2-7b-chat-hf
+library_name: peft
+tags:
+- generated_from_trainer
+model-index:
+- name: train_model
+  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. -->
+
+# train_model
+
+This model is a fine-tuned version of [NousResearch/Llama-2-7b-chat-hf](https://huggingface.co/NousResearch/Llama-2-7b-chat-hf) 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: 0.0001
+- train_batch_size: 256
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 512
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.13.2.dev0
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
+  "bias": "none",
+  "exclude_modules": null,
+  "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": 64,
+  "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": [
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "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 sha256:47bf8b7e81bbd3511cb8bd19e595befd4174d0544bc4d44804945cac545fe48c
+size 80013120

ds_config.json

@@ -0,0 +1,13 @@
+{
+    "fp16": {
+      "enabled": true
+    },
+    "zero_optimization": {
+      "stage": 2
+    },
+    "checkpoint": {
+    "disable_checkpointing": true
+  },
+    "gradient_accumulation_steps": 2
+  }
+  

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8c17011a25edaa2307214316523c819d8fd8a787d0019f377f4903c88c6301b
+size 6048