saiga_demo

README.md

@@ -0,0 +1,69 @@
+---
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: TheBloke/Llama-2-7B-fp16
+model-index:
+- name: saiga_1st_attempt
+  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. -->
+
+# saiga_1st_attempt
+
+This model is a fine-tuned version of [TheBloke/Llama-2-7B-fp16](https://huggingface.co/TheBloke/Llama-2-7B-fp16) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7981
+
+## 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: 0.0003
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 10
+- total_train_batch_size: 20
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 100
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.7044        | 1.43  | 10   | 1.6775          |
+| 1.6147        | 2.86  | 20   | 1.6721          |
+| 1.5209        | 4.29  | 30   | 1.6832          |
+| 1.4711        | 5.71  | 40   | 1.7075          |
+| 1.4222        | 7.14  | 50   | 1.7207          |
+| 1.3594        | 8.57  | 60   | 1.7500          |
+| 1.3276        | 10.0  | 70   | 1.7686          |
+| 1.2995        | 11.43 | 80   | 1.7832          |
+| 1.2516        | 12.86 | 90   | 1.7999          |
+| 1.2647        | 14.29 | 100  | 1.7981          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.39.3
+- Pytorch 2.2.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TheBloke/Llama-2-7B-fp16",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_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 sha256:2a01ed7a5c867c3b13d6ac7869e1458ba56faffcfe5a84e9ef6ecf5020461c5c
+size 33589040

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8073d0ca4ed65ea0558212eef450e90571128ff4c6963fe51228e0494450b50b
+size 4920