fernandals/llama-2-7b-news-gen

README.md

@@ -0,0 +1,100 @@
+---
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: NousResearch/Llama-2-7b-hf
+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 [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9343
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.7949        | 0.1   | 25   | 1.7390          |
+| 1.7268        | 0.21  | 50   | 1.6898          |
+| 1.7214        | 0.31  | 75   | 1.6547          |
+| 1.6573        | 0.41  | 100  | 1.6260          |
+| 1.6663        | 0.52  | 125  | 1.5999          |
+| 1.6499        | 0.62  | 150  | 1.5735          |
+| 1.61          | 0.72  | 175  | 1.5483          |
+| 1.6491        | 0.82  | 200  | 1.5288          |
+| 1.6441        | 0.93  | 225  | 1.5034          |
+| 1.5055        | 1.03  | 250  | 1.4753          |
+| 1.4955        | 1.13  | 275  | 1.4409          |
+| 1.4345        | 1.24  | 300  | 1.4159          |
+| 1.449         | 1.34  | 325  | 1.3918          |
+| 1.4762        | 1.44  | 350  | 1.3701          |
+| 1.4562        | 1.55  | 375  | 1.3449          |
+| 1.4092        | 1.65  | 400  | 1.3205          |
+| 1.4173        | 1.75  | 425  | 1.3000          |
+| 1.4225        | 1.86  | 450  | 1.2798          |
+| 1.4358        | 1.96  | 475  | 1.2600          |
+| 1.2387        | 2.06  | 500  | 1.2198          |
+| 1.232         | 2.16  | 525  | 1.1936          |
+| 1.2212        | 2.27  | 550  | 1.1720          |
+| 1.2066        | 2.37  | 575  | 1.1491          |
+| 1.199         | 2.47  | 600  | 1.1301          |
+| 1.2365        | 2.58  | 625  | 1.1124          |
+| 1.2124        | 2.68  | 650  | 1.0934          |
+| 1.2113        | 2.78  | 675  | 1.0766          |
+| 1.1947        | 2.89  | 700  | 1.0620          |
+| 1.2041        | 2.99  | 725  | 1.0441          |
+| 1.0437        | 3.09  | 750  | 1.0133          |
+| 1.0239        | 3.2   | 775  | 0.9972          |
+| 1.0417        | 3.3   | 800  | 0.9839          |
+| 0.9909        | 3.4   | 825  | 0.9712          |
+| 1.0275        | 3.51  | 850  | 0.9600          |
+| 1.0466        | 3.61  | 875  | 0.9516          |
+| 1.0036        | 3.71  | 900  | 0.9423          |
+| 1.0039        | 3.81  | 925  | 0.9363          |
+| 0.9786        | 3.92  | 950  | 0.9343          |
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.37.2
+- Pytorch 2.2.0+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.1

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "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": 32,
+  "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": [
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5df1bc65e154b644b1a56fcf37cb7942e679546004264bc460bb5f87af55f6a2
+size 159967880

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": "<unk>",
+  "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": "<unk>",
+  "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:dddf22dc36607eaa1d9fd5d263b08aee52ded9a1d78ccf73d7c13bb63284cff4
+size 4664