exLong-with-name: Lora finetuned CodeLlama-7b model

adapter_config.json

@@ -0,0 +1,34 @@
+{
+    "alpha_pattern": {},
+    "auto_mapping": null,
+    "base_model_name_or_path": "codellama/CodeLlama-7b-Instruct-hf",
+    "bias": "none",
+    "fan_in_fan_out": null,
+    "inference_mode": true,
+    "init_lora_weights": true,
+    "layer_replication": null,
+    "layers_pattern": null,
+    "layers_to_transform": null,
+    "loftq_config": {},
+    "lora_alpha": 16,
+    "lora_dropout": 0.05,
+    "megatron_config": null,
+    "megatron_core": "megatron.core",
+    "modules_to_save": null,
+    "peft_type": "LORA",
+    "r": 32,
+    "rank_pattern": {},
+    "revision": null,
+    "target_modules": [
+        "down_proj",
+        "k_proj",
+        "o_proj",
+        "v_proj",
+        "gate_proj",
+        "q_proj",
+        "up_proj"
+    ],
+    "task_type": "CAUSAL_LM",
+    "use_dora": false,
+    "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b36a6bbf3e5cc8083c7f27bb292a084cf36135f6c40b268a40a0d4d5818fde3c
+size 319977674

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "▁<EOT>": 32003,
+  "▁<MID>": 32001,
+  "▁<PRE>": 32000,
+  "▁<SUF>": 32002
+}

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "codellama/CodeLlama-7b-Instruct-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32016
+}

logs.txt

@@ -0,0 +1,161 @@
+---
+license: llama2
+base_model: codellama/CodeLlama-7b-Instruct-hf
+tags:
+- generated_from_trainer
+library_name: peft
+model-index:
+- name: work/10283/sarella/ls6/exlong-internal/_work/exp/conditionnestack2e-with-name-ft/lora-codellama-7b-123
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+adapter: lora
+base_model: codellama/CodeLlama-7b-Instruct-hf
+base_model_config: codellama/CodeLlama-7b-Instruct-hf
+bf16: true
+dataset_prepared_path: null
+datasets:
+- path: /work/10283/sarella/ls6/exlong-internal/_work/setup/conditionnestack2e-with-name-ft/train/train/train-conditionnestack2e-with-name-ft.jsonl
+  type:
+    field_input: input
+    field_instruction: instruction
+    field_output: output
+    field_system: system
+    format: '{instruction}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: You are a helpful programming assistant and an expert Java programmer.
+      You are helping a user writing exceptional-behavior tests for their Java code.
+debug: null
+deepspeed: null
+early_stopping_patience: null
+eval_sample_packing: false
+eval_steps: 20
+flash_attention: true
+fp16: false
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 8
+gradient_checkpointing: true
+group_by_length: false
+is_llama_derived_model: true
+learning_rate: 0.0002
+load_in_4bit: false
+load_in_8bit: true
+local_rank: null
+logging_steps: 1
+lora_alpha: 16
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 32
+lora_target_linear: true
+lr_scheduler: cosine
+micro_batch_size: 4
+model_type: LlamaForCausalLM
+num_epochs: 3
+optimizer: adamw_bnb_8bit
+output_dir: /work/10283/sarella/ls6/exlong-internal/_work/exp/conditionnestack2e-with-name-ft/lora-codellama-7b-123
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+sample_packing: true
+save_steps: null
+seed: 123
+sequence_len: 4096
+special_tokens:
+  bos_token: <s>
+  eos_token: </s>
+  unk_token: <unk>
+strict: false
+tf32: false
+tokenizer_type: CodeLlamaTokenizer
+train_on_inputs: false
+val_set_size: 0.01
+wandb_entity: null
+wandb_log_model: null
+wandb_project: null
+wandb_run_id: null
+wandb_watch: null
+warmup_steps: 10
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# work/10283/sarella/ls6/exlong-internal/_work/exp/conditionnestack2e-with-name-ft/lora-codellama-7b-123
+
+This model is a fine-tuned version of [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2909
+
+## 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: 4
+- seed: 123
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.631         | 0.01  | 1    | 0.7976          |
+| 0.2584        | 0.16  | 20   | 0.3000          |
+| 0.2045        | 0.31  | 40   | 0.2802          |
+| 0.1596        | 0.47  | 60   | 0.2725          |
+| 0.2024        | 0.62  | 80   | 0.2715          |
+| 0.1613        | 0.78  | 100  | 0.2638          |
+| 0.1341        | 0.93  | 120  | 0.2638          |
+| 0.1295        | 1.07  | 140  | 0.2672          |
+| 0.122         | 1.22  | 160  | 0.2694          |
+| 0.1247        | 1.38  | 180  | 0.2711          |
+| 0.1344        | 1.53  | 200  | 0.2733          |
+| 0.1329        | 1.69  | 220  | 0.2796          |
+| 0.1095        | 1.85  | 240  | 0.2731          |
+| 0.1167        | 2.0   | 260  | 0.2751          |
+| 0.0929        | 2.14  | 280  | 0.2849          |
+| 0.1112        | 2.3   | 300  | 0.2927          |
+| 0.1132        | 2.45  | 320  | 0.2856          |
+| 0.0876        | 2.61  | 340  | 0.2915          |
+| 0.0982        | 2.76  | 360  | 0.2894          |
+| 0.1042        | 2.92  | 380  | 0.2909          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.39.0.dev0
+- Pytorch 2.1.2
+- Datasets 2.18.0
+- Tokenizers 0.15.0

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.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json

@@ -0,0 +1,86 @@
+{
+  "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_first": false,
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}