Upload 8 files

README.md

@@ -1,9 +1,179 @@
 ---
+license: apache-2.0
 library_name: peft
+tags:
+- generated_from_trainer
+base_model: NurtureAI/OpenHermes-2.5-Mistral-7B-16k
+model-index:
+- name: qlora-out
+  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: `0.3.0`
+```yaml
+base_model: NurtureAI/OpenHermes-2.5-Mistral-7B-16k
+model_type: MistralForCausalLM
+tokenizer_type: LlamaTokenizer
+is_mistral_derived_model: true
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+datasets:
+  - path: Crystalcareai/WATOP600
+    type: alpaca
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.1
+output_dir: ./qlora-out
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 16000
+sample_packing: true
+pad_to_sequence_len: true
+
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+lora_target_modules:
+  - gate_proj
+  - down_proj
+  - up_proj
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+
+# Added line to resolve the error
+lora_modules_to_save: ['embed_tokens', 'lm_head']
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 1
+num_epochs: 1.5
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16: false
+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: 4
+eval_table_size:
+eval_table_max_new_tokens: 128
+saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"
+
+```
+
+</details><br>
+
+# qlora-out
+
+This model is a fine-tuned version of [NurtureAI/OpenHermes-2.5-Mistral-7B-16k](https://huggingface.co/NurtureAI/OpenHermes-2.5-Mistral-7B-16k) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5566
+
+## 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: 1
+- eval_batch_size: 1
+- 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: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 1.5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.0027        | 0.03  | 1    | 0.9286          |
+| 0.8464        | 0.27  | 9    | 0.7312          |
+| 0.5254        | 0.54  | 18   | 0.6451          |
+| 0.712         | 0.81  | 27   | 0.5988          |
+| 0.5733        | 1.01  | 36   | 0.5616          |
+| 0.3739        | 1.28  | 45   | 0.5566          |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.0.1+cu117
+- Datasets 2.16.1
+- Tokenizers 0.15.0
 ## Training procedure
 
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
 ### Framework versions
 
 
-- PEFT 0.5.0
+- PEFT 0.6.0

adapter_config.json

@@ -1,23 +1,31 @@
 {
+  "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "HuggingFaceH4/zephyr-7b-alpha",
+  "base_model_name_or_path": "NurtureAI/OpenHermes-2.5-Mistral-7B-16k",
   "bias": "none",
-  "fan_in_fan_out": false,
+  "fan_in_fan_out": null,
   "inference_mode": true,
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
   "lora_alpha": 16,
-  "lora_dropout": 0,
-  "modules_to_save": null,
+  "lora_dropout": 0.05,
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
   "peft_type": "LORA",
-  "r": 8,
+  "r": 32,
+  "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "k_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
     "v_proj",
-    "o_proj"
+    "k_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2b7f4b0ef8a6b008380b9149e8d97f737f23514729254a5fed32d080b5a0ac6
-size 27355402
+oid sha256:49a280210b0cf26f6a4b781ea02e4ad8132946f7fdf8a7cb35d5df5816c3b3ad
+size 860027221

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "NurtureAI/OpenHermes-2.5-Mistral-7B-16k",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "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": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "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": 100000.0,
+  "sliding_window": 16384,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.2",
+  "use_cache": false,
+  "vocab_size": 32002
+}

special_tokens_map.json

@@ -1,9 +1,4 @@
 {
-  "additional_special_tokens": [
-    "<unk>",
-    "<s>",
-    "</s>"
-  ],
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
@@ -18,13 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -23,24 +25,39 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
-  "additional_special_tokens": [
-    "<unk>",
-    "<s>",
-    "</s>"
-  ],
+  "additional_special_tokens": [],
   "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
+  "device_map": "auto",
   "eos_token": "</s>",
   "legacy": true,
+  "max_length": 16384,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "</s>",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
-  "truncation_side": "left",
+  "trust_remote_code": false,
   "unk_token": "<unk>",
-  "use_default_system_prompt": true
+  "use_default_system_prompt": true,
+  "use_fast": true
 }