marschub/llama1b-lora1

README.md

@@ -0,0 +1,64 @@
+---
+library_name: peft
+license: llama3.2
+base_model: meta-llama/Llama-3.2-1B
+tags:
+- generated_from_trainer
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
+
+## 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: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.6747        | 0.1593 | 500  | nan             |
+| 0.0           | 0.3187 | 1000 | nan             |
+| 0.0           | 0.4780 | 1500 | nan             |
+| 0.0           | 0.6373 | 2000 | nan             |
+| 0.0           | 0.7967 | 2500 | nan             |
+| 0.0           | 0.9560 | 3000 | nan             |
+
+
+### Framework versions
+
+- PEFT 0.13.3.dev0
+- Transformers 4.48.0.dev0
+- Pytorch 2.3.1.post100
+- Datasets 3.1.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
+  "bias": "none",
+  "eva_config": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43c089338b393830837667e381a615b79db92dbb63d383c085ca5cbb71f35fd2
+size 3424552

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c97b1853ed7dae6b8a94c4fc75c28c4d97c191382d7690b3b51cd2309d11762a
+size 5304