init

README.md

@@ -0,0 +1,171 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- axolotl
+- generated_from_trainer
+base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
+model-index:
+- name: mixtral-lora-less-modules
+  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
+base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
+model_type: AutoModelForCausalLM
+tokenizer_type: LlamaTokenizer
+is_mistral_derived_model: true
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+chat_template: inst
+
+datasets:
+  - path: ./data/raw_format/tool_used_training.jsonl
+    type: sharegpt
+    conversation: mistral
+  - path: ./data/raw_format/tool_not_used_training.jsonl
+    type: sharegpt
+    conversation: mistral
+  - path: ./data/raw_format/no_tools_training.jsonl
+    type: sharegpt
+    conversation: mistral
+
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.01
+output_dir: ./mixtral-lora-2-epochs-r64
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 4096
+sample_packing: true
+pad_to_sequence_len: true
+
+lora_r: 64
+lora_alpha: 64
+lora_dropout: 0.05
+lora_fan_in_fan_out:
+hub_model_id: liuylhf/mixtral-lora-less-modules
+hub_strategy: end
+
+lora_target_modules:
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+
+wandb_project: function-call
+wandb_name: mixtral-instruct-raw-data-v3
+wandb_log_model: end
+
+gradient_accumulation_steps: 4
+micro_batch_size: 2
+num_epochs: 4
+optimizer: paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 0.001
+adam_beta2: 0.95
+adam_epsilon: 0.00001
+max_grad_norm: 1.0
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+# loss_watchdog_threshold: 5.0
+# loss_watchdog_patience: 3
+
+warmup_steps: 10
+# evals_per_epoch: 20
+eval_steps: 0.1
+save_steps: 0.1
+eval_table_size:
+eval_max_new_tokens: 256
+# saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 1.0
+fsdp:
+fsdp_config:
+```
+
+</details><br>
+
+# mixtral-lora-less-modules
+
+This model is a fine-tuned version of [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1904
+
+## 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: 0.001
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- total_eval_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.2966        | 0.0   | 1    | 3.2222          |
+| 0.1826        | 0.4   | 123  | 0.2012          |
+| 0.1729        | 0.8   | 246  | 0.1925          |
+| 0.1852        | 1.19  | 369  | 0.1913          |
+| 0.1463        | 1.59  | 492  | 0.1857          |
+| 0.1246        | 1.99  | 615  | 0.1840          |
+| 0.1149        | 2.37  | 738  | 0.1872          |
+| 0.076         | 2.77  | 861  | 0.1837          |
+| 0.0763        | 3.15  | 984  | 0.1920          |
+| 0.0906        | 3.56  | 1107 | 0.1904          |
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.39.0.dev0
+- Pytorch 2.2.0+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b736f258bbb6518c5c6320e3be740ea54cf01ad2bc94e6b90be1ee7c5199315
+size 218196746

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bd14376b2f68b0c33a669ad954dd4a0f21b6ff2c5861b9ffc7865fdf6749503
+size 218138576

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "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-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.02,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e7d1c82c017295bf67e72f2f9c3276671b5c7c5e56727f36146b9af4b7bc72e
+size 5624