Model save

.ipynb_checkpoints/llama3_lora_sft-checkpoint.yaml

@@ -0,0 +1,44 @@
+### model
+model_name_or_path: tiiuae/falcon-7b-instruct
+adapter_name_or_path: chchen/Falcon-7B-Instruct-ORPO
+
+### method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: all
+
+### dataset
+dataset: bct_non_cot_sft_1000
+dataset_dir: data_private
+template: falcon
+cutoff_len: 1024
+# max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/Falcon-7B-Instruct/lora/orpo-sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+save_total_limit: 3
+load_best_model_at_end: true
+push_to_hub: true
+hub_model_id: chchen/Falcon-7B-Instruct-ORPO-SFT
+
+### train
+per_device_train_batch_size: 2
+gradient_accumulation_steps: 8
+learning_rate: 0.000005
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+fp16: true
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 2
+evaluation_strategy: steps
+eval_steps: 500

README.md

@@ -0,0 +1,59 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- llama-factory
+- generated_from_trainer
+base_model: tiiuae/falcon-7b-instruct
+model-index:
+- name: Falcon-7B-Instruct-ORPO-SFT
+  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. -->
+
+# Falcon-7B-Instruct-ORPO-SFT
+
+This model is a fine-tuned version of [tiiuae/falcon-7b-instruct](https://huggingface.co/tiiuae/falcon-7b-instruct) on an unknown dataset.
+
+## 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: 5e-06
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.1
+- num_epochs: 3.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.1
+- Pytorch 2.3.0
+- Datasets 2.19.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "tiiuae/falcon-7b-instruct",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_key_value",
+    "dense_h_to_4h",
+    "dense",
+    "dense_4h_to_h"
+  ],
+  "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:f996255880a06aa5804440d398a1457ede88212dc72ada3270f593e3bebf4061
+size 65309632

llama3_lora_sft.yaml

@@ -0,0 +1,44 @@
+### model
+model_name_or_path: tiiuae/falcon-7b-instruct
+adapter_name_or_path: chchen/Falcon-7B-Instruct-ORPO
+
+### method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: all
+
+### dataset
+dataset: bct_non_cot_sft_1000
+dataset_dir: data_private
+template: falcon
+cutoff_len: 1024
+# max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/Falcon-7B-Instruct/lora/orpo-sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+save_total_limit: 3
+load_best_model_at_end: true
+push_to_hub: true
+hub_model_id: chchen/Falcon-7B-Instruct-ORPO-SFT
+
+### train
+per_device_train_batch_size: 2
+gradient_accumulation_steps: 8
+learning_rate: 0.000005
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+fp16: true
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 2
+evaluation_strategy: steps
+eval_steps: 500

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,126 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": ">>TITLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": ">>ABSTRACT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": ">>INTRODUCTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": ">>SUMMARY<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": ">>COMMENT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": ">>ANSWER<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": ">>QUESTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": ">>DOMAIN<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": ">>PREFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": ">>SUFFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": ">>MIDDLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\nFalcon:' }}{% elif message['role'] == 'assistant' %}{{ content + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

trainer_log.jsonl

@@ -0,0 +1,17 @@
+{"current_steps": 10, "total_steps": 168, "loss": 0.8422, "learning_rate": 4.957230266673969e-06, "epoch": 0.17777777777777778, "percentage": 5.95, "elapsed_time": "0:00:16", "remaining_time": "0:04:23"}
+{"current_steps": 20, "total_steps": 168, "loss": 0.7171, "learning_rate": 4.828686741593921e-06, "epoch": 0.35555555555555557, "percentage": 11.9, "elapsed_time": "0:00:32", "remaining_time": "0:04:00"}
+{"current_steps": 30, "total_steps": 168, "loss": 0.5551, "learning_rate": 4.618852307232078e-06, "epoch": 0.5333333333333333, "percentage": 17.86, "elapsed_time": "0:00:48", "remaining_time": "0:03:42"}
+{"current_steps": 40, "total_steps": 168, "loss": 0.4059, "learning_rate": 4.335051964269395e-06, "epoch": 0.7111111111111111, "percentage": 23.81, "elapsed_time": "0:01:04", "remaining_time": "0:03:24"}
+{"current_steps": 50, "total_steps": 168, "loss": 0.3053, "learning_rate": 3.987192750660719e-06, "epoch": 0.8888888888888888, "percentage": 29.76, "elapsed_time": "0:01:19", "remaining_time": "0:03:08"}
+{"current_steps": 60, "total_steps": 168, "loss": 0.2825, "learning_rate": 3.587417902020876e-06, "epoch": 1.0666666666666667, "percentage": 35.71, "elapsed_time": "0:01:35", "remaining_time": "0:02:52"}
+{"current_steps": 70, "total_steps": 168, "loss": 0.2082, "learning_rate": 3.1496829497545268e-06, "epoch": 1.2444444444444445, "percentage": 41.67, "elapsed_time": "0:01:51", "remaining_time": "0:02:35"}
+{"current_steps": 80, "total_steps": 168, "loss": 0.1955, "learning_rate": 2.6892685546987724e-06, "epoch": 1.4222222222222223, "percentage": 47.62, "elapsed_time": "0:02:07", "remaining_time": "0:02:19"}
+{"current_steps": 90, "total_steps": 168, "loss": 0.2161, "learning_rate": 2.2222470825144806e-06, "epoch": 1.6, "percentage": 53.57, "elapsed_time": "0:02:22", "remaining_time": "0:02:03"}
+{"current_steps": 100, "total_steps": 168, "loss": 0.169, "learning_rate": 1.7649215418673847e-06, "epoch": 1.7777777777777777, "percentage": 59.52, "elapsed_time": "0:02:38", "remaining_time": "0:01:47"}
+{"current_steps": 110, "total_steps": 168, "loss": 0.2051, "learning_rate": 1.3332564712129845e-06, "epoch": 1.9555555555555557, "percentage": 65.48, "elapsed_time": "0:02:54", "remaining_time": "0:01:31"}
+{"current_steps": 120, "total_steps": 168, "loss": 0.2007, "learning_rate": 9.423206410612498e-07, "epoch": 2.1333333333333333, "percentage": 71.43, "elapsed_time": "0:03:09", "remaining_time": "0:01:15"}
+{"current_steps": 130, "total_steps": 168, "loss": 0.1866, "learning_rate": 6.057610261367044e-07, "epoch": 2.311111111111111, "percentage": 77.38, "elapsed_time": "0:03:25", "remaining_time": "0:01:00"}
+{"current_steps": 140, "total_steps": 168, "loss": 0.2212, "learning_rate": 3.3532641026504415e-07, "epoch": 2.488888888888889, "percentage": 83.33, "elapsed_time": "0:03:41", "remaining_time": "0:00:44"}
+{"current_steps": 150, "total_steps": 168, "loss": 0.1776, "learning_rate": 1.4045725421448332e-07, "epoch": 2.6666666666666665, "percentage": 89.29, "elapsed_time": "0:03:56", "remaining_time": "0:00:28"}
+{"current_steps": 160, "total_steps": 168, "loss": 0.1686, "learning_rate": 2.7956143581177874e-08, "epoch": 2.8444444444444446, "percentage": 95.24, "elapsed_time": "0:04:11", "remaining_time": "0:00:12"}
+{"current_steps": 168, "total_steps": 168, "epoch": 2.986666666666667, "percentage": 100.0, "elapsed_time": "0:04:24", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56cfcd67ac4c548c481e0e5a8e0735d022ec22fd4a6e0a561b75eeba041857e0
+size 5240