HarshalH/SFT_LoRA

README.md

@@ -1,13 +1,13 @@
 ---
-library_name: transformers
-license: mit
 base_model: gpt2
+datasets:
+- generator
+library_name: peft
+license: mit
 tags:
 - trl
 - sft
 - generated_from_trainer
-datasets:
-- generator
 model-index:
 - name: output_dir
   results: []
@@ -45,9 +45,14 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 1
 
+### Training results
+
+
+
 ### Framework versions
 
+- PEFT 0.13.0
 - Transformers 4.44.2
 - Pytorch 2.4.0
 - Datasets 3.0.0
-- Tokenizers 0.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "gpt2",
+  "bias": "none",
+  "fan_in_fan_out": true,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_attn"
+  ],
+  "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 sha256:2e5dfe949830c95c3eae2c6e21935af6b0e3a103f29bd6d32d03e9f759849aff
+size 9440280

runs/Oct02_00-52-07_d41decf1c6dc/events.out.tfevents.1727830332.d41decf1c6dc.30.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7859ae5427f38457dd677ad1d9223922441fc8c876155915ebdbe2338568e273
+size 5827

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1eb340bde088335e0b005c4962b0d7d6a01d7ff441befe68f2a4dcb65d35516
+oid sha256:9cd081b6455b22e7eea6cf22b5fdc47808f9967f59b548db0315d2ca0b747b96
 size 5496