Initial commit of the model

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+datasets:
+- arcee-ai/Zilo-Filtered-SQL-Instruct-v2
+model-index:
+- name: zilo-instruct-v2-sft-qlora
+  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. -->
+
+# zilo-instruct-v2-sft-qlora
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the arcee-ai/Zilo-Filtered-SQL-Instruct-v2 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6246
+
+## 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: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.7588        | 0.9899 | 49   | 0.7386          |
+| 0.6201        | 2.0    | 99   | 0.6307          |
+| 0.6087        | 2.9697 | 147  | 0.6246          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "k_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:e1a7c5ba3953bb0b3141884f066d930329b6e5947c0a580e0ee9b4f54c973f98
+size 83946192

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 2.9696969696969697,
+    "eval_loss": 0.6245681643486023,
+    "eval_runtime": 17.323,
+    "eval_samples": 1371,
+    "eval_samples_per_second": 2.482,
+    "eval_steps_per_second": 0.346,
+    "total_flos": 2.0566538541072384e+17,
+    "train_loss": 0.7671454966473742,
+    "train_runtime": 1686.4021,
+    "train_samples": 12338,
+    "train_samples_per_second": 0.699,
+    "train_steps_per_second": 0.087
+}

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "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": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "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": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9696969696969697,
+    "eval_loss": 0.6245681643486023,
+    "eval_runtime": 17.323,
+    "eval_samples": 1371,
+    "eval_samples_per_second": 2.482,
+    "eval_steps_per_second": 0.346
+}

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 +1,43 @@
+{
+  "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
+    }
+  },
+  "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 %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.9696969696969697,
+    "total_flos": 2.0566538541072384e+17,
+    "train_loss": 0.7671454966473742,
+    "train_runtime": 1686.4021,
+    "train_samples": 12338,
+    "train_samples_per_second": 0.699,
+    "train_steps_per_second": 0.087
+}

trainer_state.json

@@ -0,0 +1,276 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9696969696969697,
+  "eval_steps": 500,
+  "global_step": 147,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.020202020202020204,
+      "grad_norm": 2.578125,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 1.5448,
+      "step": 1
+    },
+    {
+      "epoch": 0.10101010101010101,
+      "grad_norm": 2.546875,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.5503,
+      "step": 5
+    },
+    {
+      "epoch": 0.20202020202020202,
+      "grad_norm": 2.390625,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.469,
+      "step": 10
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 1.65625,
+      "learning_rate": 2e-05,
+      "loss": 1.2465,
+      "step": 15
+    },
+    {
+      "epoch": 0.40404040404040403,
+      "grad_norm": 1.203125,
+      "learning_rate": 1.9929278846732883e-05,
+      "loss": 1.0305,
+      "step": 20
+    },
+    {
+      "epoch": 0.5050505050505051,
+      "grad_norm": 0.953125,
+      "learning_rate": 1.9718115683235418e-05,
+      "loss": 0.9205,
+      "step": 25
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 0.609375,
+      "learning_rate": 1.936949724999762e-05,
+      "loss": 0.8521,
+      "step": 30
+    },
+    {
+      "epoch": 0.7070707070707071,
+      "grad_norm": 0.48046875,
+      "learning_rate": 1.8888354486549238e-05,
+      "loss": 0.8354,
+      "step": 35
+    },
+    {
+      "epoch": 0.8080808080808081,
+      "grad_norm": 0.478515625,
+      "learning_rate": 1.8281492787113707e-05,
+      "loss": 0.7916,
+      "step": 40
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.46484375,
+      "learning_rate": 1.7557495743542586e-05,
+      "loss": 0.7588,
+      "step": 45
+    },
+    {
+      "epoch": 0.98989898989899,
+      "eval_loss": 0.7386298179626465,
+      "eval_runtime": 17.3037,
+      "eval_samples_per_second": 2.485,
+      "eval_steps_per_second": 0.347,
+      "step": 49
+    },
+    {
+      "epoch": 1.0101010101010102,
+      "grad_norm": 0.5390625,
+      "learning_rate": 1.6726603737012527e-05,
+      "loss": 0.7461,
+      "step": 50
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.5078125,
+      "learning_rate": 1.5800569095711983e-05,
+      "loss": 0.715,
+      "step": 55
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "grad_norm": 0.3046875,
+      "learning_rate": 1.479248986720057e-05,
+      "loss": 0.6996,
+      "step": 60
+    },
+    {
+      "epoch": 1.3131313131313131,
+      "grad_norm": 0.28125,
+      "learning_rate": 1.3716624556603275e-05,
+      "loss": 0.6809,
+      "step": 65
+    },
+    {
+      "epoch": 1.4141414141414141,
+      "grad_norm": 0.318359375,
+      "learning_rate": 1.2588190451025209e-05,
+      "loss": 0.6585,
+      "step": 70
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "grad_norm": 0.2255859375,
+      "learning_rate": 1.1423148382732854e-05,
+      "loss": 0.6599,
+      "step": 75
+    },
+    {
+      "epoch": 1.6161616161616161,
+      "grad_norm": 0.2431640625,
+      "learning_rate": 1.0237976975461074e-05,
+      "loss": 0.646,
+      "step": 80
+    },
+    {
+      "epoch": 1.7171717171717171,
+      "grad_norm": 0.203125,
+      "learning_rate": 9.049439566958176e-06,
+      "loss": 0.6349,
+      "step": 85
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.2392578125,
+      "learning_rate": 7.874347104470234e-06,
+      "loss": 0.6352,
+      "step": 90
+    },
+    {
+      "epoch": 1.9191919191919191,
+      "grad_norm": 0.2060546875,
+      "learning_rate": 6.729320366825785e-06,
+      "loss": 0.6201,
+      "step": 95
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6306869983673096,
+      "eval_runtime": 17.31,
+      "eval_samples_per_second": 2.484,
+      "eval_steps_per_second": 0.347,
+      "step": 99
+    },
+    {
+      "epoch": 2.0202020202020203,
+      "grad_norm": 0.2001953125,
+      "learning_rate": 5.630554876306407e-06,
+      "loss": 0.6233,
+      "step": 100
+    },
+    {
+      "epoch": 2.121212121212121,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 4.593591825444028e-06,
+      "loss": 0.6138,
+      "step": 105
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 3.633098258809119e-06,
+      "loss": 0.6218,
+      "step": 110
+    },
+    {
+      "epoch": 2.323232323232323,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 2.7626596189492983e-06,
+      "loss": 0.6201,
+      "step": 115
+    },
+    {
+      "epoch": 2.4242424242424243,
+      "grad_norm": 0.19921875,
+      "learning_rate": 1.994587590756397e-06,
+      "loss": 0.6164,
+      "step": 120
+    },
+    {
+      "epoch": 2.525252525252525,
+      "grad_norm": 0.2041015625,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 0.6157,
+      "step": 125
+    },
+    {
+      "epoch": 2.6262626262626263,
+      "grad_norm": 0.216796875,
+      "learning_rate": 8.073969641833446e-07,
+      "loss": 0.6151,
+      "step": 130
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.267578125,
+      "learning_rate": 4.0507026385502747e-07,
+      "loss": 0.6097,
+      "step": 135
+    },
+    {
+      "epoch": 2.8282828282828283,
+      "grad_norm": 0.208984375,
+      "learning_rate": 1.3845646281813508e-07,
+      "loss": 0.617,
+      "step": 140
+    },
+    {
+      "epoch": 2.929292929292929,
+      "grad_norm": 0.1943359375,
+      "learning_rate": 1.1326608169920373e-08,
+      "loss": 0.6087,
+      "step": 145
+    },
+    {
+      "epoch": 2.9696969696969697,
+      "eval_loss": 0.6245681643486023,
+      "eval_runtime": 17.3067,
+      "eval_samples_per_second": 2.485,
+      "eval_steps_per_second": 0.347,
+      "step": 147
+    },
+    {
+      "epoch": 2.9696969696969697,
+      "step": 147,
+      "total_flos": 2.0566538541072384e+17,
+      "train_loss": 0.7671454966473742,
+      "train_runtime": 1686.4021,
+      "train_samples_per_second": 0.699,
+      "train_steps_per_second": 0.087
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 147,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.0566538541072384e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd2997d6445ea8ca8ea9f3372dfb082e7bc361b6693cb87254b6355b6e847667
+size 5176