TheBloke/CodeLlama-7B-Instruct-AWQ-FaVe-rank8-10epochs

README.md

@@ -0,0 +1,100 @@
+---
+license: llama2
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: TheBloke/CodeLlama-7B-Instruct-AWQ
+model-index:
+- name: CodeLlama-7B-Instruct-AWQ-FaVe-rank8-10epochs
+  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. -->
+
+# CodeLlama-7B-Instruct-AWQ-FaVe-rank8-10epochs
+
+This model is a fine-tuned version of [TheBloke/CodeLlama-7B-Instruct-AWQ](https://huggingface.co/TheBloke/CodeLlama-7B-Instruct-AWQ) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4895
+
+## 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: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| No log        | 0.2685 | 10   | 2.3646          |
+| 2.4179        | 0.5369 | 20   | 2.1518          |
+| 2.4179        | 0.8054 | 30   | 1.7627          |
+| 1.8436        | 1.0738 | 40   | 1.4048          |
+| 1.8436        | 1.3423 | 50   | 1.0944          |
+| 1.1066        | 1.6107 | 60   | 0.9634          |
+| 1.1066        | 1.8792 | 70   | 0.8695          |
+| 0.7716        | 2.1477 | 80   | 0.7980          |
+| 0.7716        | 2.4161 | 90   | 0.7575          |
+| 0.6585        | 2.6846 | 100  | 0.7293          |
+| 0.6585        | 2.9530 | 110  | 0.6901          |
+| 0.6067        | 3.2215 | 120  | 0.6729          |
+| 0.6067        | 3.4899 | 130  | 0.6452          |
+| 0.5672        | 3.7584 | 140  | 0.6255          |
+| 0.5672        | 4.0268 | 150  | 0.6129          |
+| 0.5196        | 4.2953 | 160  | 0.5954          |
+| 0.5196        | 4.5638 | 170  | 0.5747          |
+| 0.4492        | 4.8322 | 180  | 0.5668          |
+| 0.4492        | 5.1007 | 190  | 0.5590          |
+| 0.4539        | 5.3691 | 200  | 0.5435          |
+| 0.4539        | 5.6376 | 210  | 0.5397          |
+| 0.3938        | 5.9060 | 220  | 0.5359          |
+| 0.3938        | 6.1745 | 230  | 0.5188          |
+| 0.3748        | 6.4430 | 240  | 0.5247          |
+| 0.3748        | 6.7114 | 250  | 0.5190          |
+| 0.3759        | 6.9799 | 260  | 0.5069          |
+| 0.3759        | 7.2483 | 270  | 0.4995          |
+| 0.3308        | 7.5168 | 280  | 0.5114          |
+| 0.3308        | 7.7852 | 290  | 0.5004          |
+| 0.3259        | 8.0537 | 300  | 0.4937          |
+| 0.3259        | 8.3221 | 310  | 0.4990          |
+| 0.3023        | 8.5906 | 320  | 0.4964          |
+| 0.3023        | 8.8591 | 330  | 0.4904          |
+| 0.3036        | 9.1275 | 340  | 0.4898          |
+| 0.3036        | 9.3960 | 350  | 0.4914          |
+| 0.3118        | 9.6644 | 360  | 0.4897          |
+| 0.3118        | 9.9329 | 370  | 0.4895          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.2
+- Pytorch 2.2.1+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": "TheBloke/CodeLlama-7B-Instruct-AWQ",
+  "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": 8,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "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:b749afdc37208ffce089d20514e270b2c0d025f662c27a7141da4d22cf7e92ad
+size 16794200

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,83 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d7a193f13c6ed675bfe1f91969725422f4f67b798cd8de0a7d868dfcaa9caf9
+size 5112