End of training

README.md

@@ -1,3 +1,153 @@
----
-license: mit
----
+---
+library_name: peft
+license: other
+base_model: deepseek-ai/deepseek-coder-6.7b-instruct
+tags:
+- axolotl
+- base_model:adapter:deepseek-ai/deepseek-coder-6.7b-instruct
+- lora
+- transformers
+datasets:
+- darwinkernelpanic/luau_corpus_axolotl
+pipeline_tag: text-generation
+model-index:
+- name: deepseek-coder-6.7b-instruct-luau
+  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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.13.0.dev0`
+```yaml
+base_model: deepseek-ai/deepseek-coder-6.7b-instruct
+hub_model_id: darwinkernelpanic/deepseek-coder-6.7b-instruct-luau
+hub_strategy: end
+trust_remote_code: true
+
+load_in_8bit: false
+load_in_4bit: true
+
+datasets:
+  - path: darwinkernelpanic/luau_corpus_axolotl
+    type: completion
+    field_instruction: prompt
+    field_output: completion
+
+dataset_prepared_path:
+val_set_size: 0.05
+output_dir: ./outputs/deepseek-luau-finetune
+
+sequence_len: 3072
+sample_packing: true
+eval_sample_packing: true
+
+adapter: qlora
+lora_model_dir:
+lora_r: 32
+lora_alpha: 32
+lora_dropout: 0.05
+lora_target_linear: true
+
+wandb_project: deepseek-luau-finetune
+wandb_entity:
+wandb_watch:
+wandb_name: deepseek-coder-6.7b-luau
+wandb_log_model:
+
+gradient_accumulation_steps: 2
+micro_batch_size: 6
+num_epochs: 3
+optimizer: adamw_torch_fused
+lr_scheduler: cosine
+learning_rate: 0.0002
+bf16: auto
+tf32: true
+
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+
+resume_from_checkpoint:
+logging_steps: 10
+flash_attention: true
+warmup_ratio: 0.1
+evals_per_epoch: 4
+saves_per_epoch: 1
+weight_decay: 0.01
+
+fsdp: []
+fsdp_config: {}
+
+special_tokens:
+  pad_token: "<|EOT|>"
+```
+
+</details><br>
+
+# deepseek-coder-6.7b-instruct-luau
+
+This model is a fine-tuned version of [deepseek-ai/deepseek-coder-6.7b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct) on the darwinkernelpanic/luau_corpus_axolotl dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6346
+- Ppl: 5.1272
+- Memory/max Active (gib): 10.65
+- Memory/max Allocated (gib): 10.65
+- Memory/device Reserved (gib): 11.93
+
+## 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: 6
+- eval_batch_size: 6
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 12
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 16
+- training_steps: 162
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Ppl     | Active (gib) | Allocated (gib) | Reserved (gib) |
+|:-------------:|:------:|:----:|:---------------:|:-------:|:------------:|:---------------:|:--------------:|
+| No log        | 0      | 0    | 3.8515          | 47.0637 | 7.0          | 7.0             | 7.26           |
+| 3.2644        | 0.2593 | 14   | 2.8645          | 17.5407 | 10.65        | 10.65           | 12.22          |
+| 2.6242        | 0.5185 | 28   | 2.2633          | 9.6147  | 12.27        | 12.27           | 14.58          |
+| 2.0431        | 0.7778 | 42   | 2.0479          | 7.7515  | 10.65        | 10.65           | 13.92          |
+| 1.9054        | 1.0370 | 56   | 1.9163          | 6.796   | 10.65        | 10.65           | 14.72          |
+| 1.7318        | 1.2963 | 70   | 1.8184          | 6.1622  | 7.61         | 7.61            | 13.92          |
+| 1.6119        | 1.5556 | 84   | 1.7550          | 5.7836  | 12.27        | 12.27           | 14.54          |
+| 1.6022        | 1.8148 | 98   | 1.7048          | 5.5006  | 10.65        | 10.65           | 14.23          |
+| 1.6249        | 2.0741 | 112  | 1.6723          | 5.3242  | 10.65        | 10.65           | 13.99          |
+| 1.4995        | 2.3333 | 126  | 1.6503          | 5.2088  | 10.65        | 10.65           | 11.93          |
+| 1.4803        | 2.5926 | 140  | 1.6381          | 5.1452  | 7.61         | 7.61            | 14.58          |
+| 1.4872        | 2.8519 | 154  | 1.6346          | 5.1272  | 10.65        | 10.65           | 11.93          |
+
+
+### Framework versions
+
+- PEFT 0.18.0
+- Transformers 4.57.1
+- Pytorch 2.8.0+cu128
+- Datasets 4.4.1
+- Tokenizers 0.22.1

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d72763e0fec0fd3f48f68a77f8f9afed9f9e61d6de1dc393f5765939f8fd9710
+size 319876032

chat_template.jinja

@@ -0,0 +1,26 @@
+{% if not add_generation_prompt is defined %}
+{% set add_generation_prompt = false %}
+{% endif %}
+{%- set ns = namespace(found=false) -%}
+{%- for message in messages -%}
+    {%- if message['role'] == 'system' -%}
+        {%- set ns.found = true -%}
+    {%- endif -%}
+{%- endfor -%}
+{{bos_token}}{%- if not ns.found -%}
+{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\n'}}
+{%- endif %}
+{%- for message in messages %}
+    {%- if message['role'] == 'system' %}
+{{ message['content'] }}
+    {%- else %}
+        {%- if message['role'] == 'user' %}
+{{'### Instruction:\n' + message['content'] + '\n'}}
+        {%- else %}
+{{'### Response:\n' + message['content'] + '\n<|EOT|>\n'}}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{% if add_generation_prompt %}
+{{'### Response:'}}
+{% endif %}

config.json

@@ -0,0 +1,48 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 32013,
+  "dtype": "bfloat16",
+  "eos_token_id": 32021,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 16384,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "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": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "rope_type": "linear",
+    "type": "linear"
+  },
+  "rope_theta": 100000,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "vocab_size": 32256
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,194 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|EOT|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<|EOT|>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c27fbd9e94f449281717b151184d446a615170e5efaa42d4022dcd869cf6ea9a
+size 7441