lillybak/

README.md

@@ -0,0 +1,87 @@
+---
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+base_model: NousResearch/Llama-2-7b-hf
+model-index:
+- name: llama2_instruct_generation
+  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. -->
+
+# llama2_instruct_generation
+
+This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6717
+
+## 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: 0.0002
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_steps: 20
+- training_steps: 500
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.9453        | 0.0   | 20   | 1.8075          |
+| 1.8785        | 0.01  | 40   | 1.7784          |
+| 1.8857        | 0.01  | 60   | 1.7662          |
+| 1.8799        | 0.01  | 80   | 1.7530          |
+| 1.9231        | 0.01  | 100  | 1.7425          |
+| 1.813         | 0.02  | 120  | 1.7142          |
+| 1.8755        | 0.02  | 140  | 1.7035          |
+| 1.8051        | 0.02  | 160  | 1.6975          |
+| 1.7347        | 0.02  | 180  | 1.6927          |
+| 1.7275        | 0.03  | 200  | 1.6907          |
+| 1.8213        | 0.03  | 220  | 1.6882          |
+| 1.7671        | 0.03  | 240  | 1.6851          |
+| 1.7736        | 0.04  | 260  | 1.6839          |
+| 1.8085        | 0.04  | 280  | 1.6826          |
+| 1.74          | 0.04  | 300  | 1.6803          |
+| 1.7354        | 0.04  | 320  | 1.6789          |
+| 1.7736        | 0.05  | 340  | 1.6808          |
+| 1.8226        | 0.05  | 360  | 1.6786          |
+| 1.7954        | 0.05  | 380  | 1.6761          |
+| 1.7472        | 0.05  | 400  | 1.6746          |
+| 1.6613        | 0.06  | 420  | 1.6736          |
+| 1.7523        | 0.06  | 440  | 1.6721          |
+| 1.7296        | 0.06  | 460  | 1.6717          |
+| 1.8324        | 0.07  | 480  | 1.6729          |
+| 1.7083        | 0.07  | 500  | 1.6717          |
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.36.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "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": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cb7f1f0e0e11e41cbfc36142ca52eaad8a167231d6d167412c76c1c4e7eaae1
+size 134235048

runs/Jan19_03-09-49_eecc8ca7797b/events.out.tfevents.1705633922.eecc8ca7797b.6044.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae2fa983a9180e8485329b4991c6de6528bccb65019f3b154bc615dbc387c92a
+size 19748

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e020bb615b29e8912d5b88f4bb96b1de759d486a405e314ecb67cc12e31b4251
+size 4728