YOUR HUGGINGFACE LOCATION HERE

README.md

@@ -0,0 +1,87 @@
+---
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: NousResearch/Llama-2-7b-hf
+datasets:
+- generator
+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: 1.6728
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.8965        | 0.0027 | 20   | 1.8107          |
+| 1.8264        | 0.0054 | 40   | 1.7808          |
+| 1.9263        | 0.0081 | 60   | 1.7669          |
+| 1.8825        | 0.0108 | 80   | 1.7538          |
+| 1.8391        | 0.0135 | 100  | 1.7324          |
+| 1.8253        | 0.0163 | 120  | 1.7068          |
+| 1.9297        | 0.0190 | 140  | 1.7029          |
+| 1.8338        | 0.0217 | 160  | 1.6985          |
+| 1.7641        | 0.0244 | 180  | 1.6939          |
+| 1.7714        | 0.0271 | 200  | 1.6916          |
+| 1.715         | 0.0298 | 220  | 1.6886          |
+| 1.7786        | 0.0325 | 240  | 1.6866          |
+| 1.716         | 0.0352 | 260  | 1.6860          |
+| 1.899         | 0.0379 | 280  | 1.6857          |
+| 1.8455        | 0.0406 | 300  | 1.6851          |
+| 1.6802        | 0.0433 | 320  | 1.6836          |
+| 1.7304        | 0.0461 | 340  | 1.6818          |
+| 1.8154        | 0.0488 | 360  | 1.6793          |
+| 1.8813        | 0.0515 | 380  | 1.6793          |
+| 1.8423        | 0.0542 | 400  | 1.6789          |
+| 1.7785        | 0.0569 | 420  | 1.6767          |
+| 1.8999        | 0.0596 | 440  | 1.6763          |
+| 1.7594        | 0.0623 | 460  | 1.6752          |
+| 1.7182        | 0.0650 | 480  | 1.6745          |
+| 1.8259        | 0.0677 | 500  | 1.6728          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "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,
+  "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": [
+    "q_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:b9f370ac89d10595863a5c400d1d0908fba7e5b0eb2cf28899b21e42240fe6e8
+size 134235048

runs/May25_07-30-58_dbfb89ea8e86/events.out.tfevents.1716622304.dbfb89ea8e86.228.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7433d7c1ba28dc8f400eccabf1bfe3ecd3483b6b7370e541e4a1689357dd3992
+size 23009

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.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

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 sha256:9729252d69e539597846b28b2bcbfe46fb8a4076e2281895ec7b56841118c91b
+size 5112