2024-12-18-15-13-12

README.md

@@ -0,0 +1,53 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+tags:
+- generated_from_trainer
+model-index:
+- name: Qwen2.5-1.5B-Instruct-prompt-injection
+  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. -->
+
+# Qwen2.5-1.5B-Instruct-prompt-injection
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) 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: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 50
+- num_epochs: 2
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.46.3
+- Pytorch 2.4.0
+- Datasets 3.1.0
+- Tokenizers 0.20.3

adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2"
+  },
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0de7981adf78b5cd6fec87b9b8f63414eaa767187d209eb18994a368160042f
+size 36981072

runs/Dec18_14-41-10_fb296a6543a6/events.out.tfevents.1734532872.fb296a6543a6.150.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b6f05eb9b72c58a36499561e293b6a11bd9248a518a680dc5b0bd6fd4555ee4
+size 5725

runs/Dec18_14-58-15_fb296a6543a6/events.out.tfevents.1734533895.fb296a6543a6.150.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c9161894d781db6c5fbf77fbc8e295b8264c2e4edf58fe67633f1dcf9ba0124
+size 5725

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9128f85f4032d1e8e8949c41b05e5aa0303cf4010c2ed2dd7ab32649ac7e4c0c
+size 5368