meta-llama/CodeLlama-7b-Instruct-hf-FaVe-rank32-10epochs

README.md

@@ -0,0 +1,100 @@
+---
+license: llama2
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: meta-llama/CodeLlama-7b-Instruct-hf
+model-index:
+- name: CodeLlama-7b-Instruct-hf-FaVe-rank32-10epochs
+  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-hf-FaVe-rank32-10epochs
+
+This model is a fine-tuned version of [meta-llama/CodeLlama-7b-Instruct-hf](https://huggingface.co/meta-llama/CodeLlama-7b-Instruct-hf) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4773
+
+## 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   | 2.1933          |
+| 2.2814        | 0.5369 | 20   | 1.6913          |
+| 2.2814        | 0.8054 | 30   | 1.1039          |
+| 1.2593        | 1.0738 | 40   | 0.7832          |
+| 1.2593        | 1.3423 | 50   | 0.6804          |
+| 0.7223        | 1.6107 | 60   | 0.6281          |
+| 0.7223        | 1.8792 | 70   | 0.5940          |
+| 0.5977        | 2.1477 | 80   | 0.5714          |
+| 0.5977        | 2.4161 | 90   | 0.5421          |
+| 0.5218        | 2.6846 | 100  | 0.5222          |
+| 0.5218        | 2.9530 | 110  | 0.5033          |
+| 0.4401        | 3.2215 | 120  | 0.4987          |
+| 0.4401        | 3.4899 | 130  | 0.4822          |
+| 0.3746        | 3.7584 | 140  | 0.4546          |
+| 0.3746        | 4.0268 | 150  | 0.4331          |
+| 0.3208        | 4.2953 | 160  | 0.4625          |
+| 0.3208        | 4.5638 | 170  | 0.4269          |
+| 0.2951        | 4.8322 | 180  | 0.4339          |
+| 0.2951        | 5.1007 | 190  | 0.4123          |
+| 0.2516        | 5.3691 | 200  | 0.4562          |
+| 0.2516        | 5.6376 | 210  | 0.4228          |
+| 0.2191        | 5.9060 | 220  | 0.4243          |
+| 0.2191        | 6.1745 | 230  | 0.4357          |
+| 0.2121        | 6.4430 | 240  | 0.4404          |
+| 0.2121        | 6.7114 | 250  | 0.4212          |
+| 0.1739        | 6.9799 | 260  | 0.4348          |
+| 0.1739        | 7.2483 | 270  | 0.4444          |
+| 0.1617        | 7.5168 | 280  | 0.4342          |
+| 0.1617        | 7.7852 | 290  | 0.4529          |
+| 0.1453        | 8.0537 | 300  | 0.4525          |
+| 0.1453        | 8.3221 | 310  | 0.4722          |
+| 0.1387        | 8.5906 | 320  | 0.4712          |
+| 0.1387        | 8.8591 | 330  | 0.4691          |
+| 0.1214        | 9.1275 | 340  | 0.4686          |
+| 0.1214        | 9.3960 | 350  | 0.4728          |
+| 0.1226        | 9.6644 | 360  | 0.4769          |
+| 0.1226        | 9.9329 | 370  | 0.4773          |
+
+
+### 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": "meta-llama/CodeLlama-7b-Instruct-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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "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 sha256:6314d2f72c8b550075602c5645021a6b56cfb0b8477f38793606c15f494b0512
+size 33571624

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 +1,84 @@
+{
+  "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>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content | trim + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content | trim + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "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:b5161acfb804a3dd1ff97de255d9c91d575d5284fe4ed4d9f1c9c4f8e11c0bdf
+size 5112