rheubanks/LLMENG2

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: 1.6705
+
+## 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: 0.03
+- training_steps: 500
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.9724        | 0.0   | 20   | 1.8100          |
+| 1.8173        | 0.01  | 40   | 1.7801          |
+| 1.8184        | 0.01  | 60   | 1.7671          |
+| 1.8725        | 0.01  | 80   | 1.7568          |
+| 1.8967        | 0.01  | 100  | 1.7460          |
+| 1.8943        | 0.02  | 120  | 1.7172          |
+| 1.788         | 0.02  | 140  | 1.7045          |
+| 1.8953        | 0.02  | 160  | 1.6986          |
+| 1.8262        | 0.02  | 180  | 1.6943          |
+| 1.8472        | 0.03  | 200  | 1.6926          |
+| 1.8416        | 0.03  | 220  | 1.6896          |
+| 1.838         | 0.03  | 240  | 1.6855          |
+| 1.7743        | 0.04  | 260  | 1.6806          |
+| 1.8562        | 0.04  | 280  | 1.6785          |
+| 1.8562        | 0.04  | 300  | 1.6794          |
+| 1.8117        | 0.04  | 320  | 1.6783          |
+| 1.8193        | 0.05  | 340  | 1.6768          |
+| 1.8807        | 0.05  | 360  | 1.6745          |
+| 1.7641        | 0.05  | 380  | 1.6738          |
+| 1.7738        | 0.05  | 400  | 1.6735          |
+| 1.7759        | 0.06  | 420  | 1.6733          |
+| 1.7089        | 0.06  | 440  | 1.6721          |
+| 1.7984        | 0.06  | 460  | 1.6706          |
+| 1.7243        | 0.07  | 480  | 1.6720          |
+| 1.9205        | 0.07  | 500  | 1.6705          |
+
+
+### 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": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bceaf834535261db0b82fa984e7892b25a7bc0ae4b8c3d6e652aae0a11386b45
+size 134235048

runs/Jan19_20-23-43_4d9c3ef3dd9e/events.out.tfevents.1705695906.4d9c3ef3dd9e.4829.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:538078efc7bc2d39ccedf6236e5d20e57c66eea56c326f2f49e6388d6b65f09a
+size 19749

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 sha256:13a108d5e4534c893c6c70911b718255e040bdd527133bd86d7a413a53c974ac
+size 4728