Upload 11 files

README.md

@@ -0,0 +1,59 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.1
+model-index:
+- name: train_2024-01-11-03-12-55
+  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. -->
+
+# train_2024-01-11-03-12-55
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the Legal_0706 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: 0.0002
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.36.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceab1fbc88fd034e3f3f3fe0aca7a8736c91dd9af4197fd1348287e0b2eaeadf
+size 13648432

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.99,
+    "train_loss": 0.9853932401713204,
+    "train_runtime": 6464.5656,
+    "train_samples_per_second": 0.68,
+    "train_steps_per_second": 0.011
+}

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,
+  "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>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.99,
+    "train_loss": 0.9853932401713204,
+    "train_runtime": 6464.5656,
+    "train_samples_per_second": 0.68,
+    "train_steps_per_second": 0.011
+}

trainer_log.jsonl

@@ -0,0 +1,14 @@
+{"current_steps": 5, "total_steps": 68, "loss": 1.1721, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001973438054360693, "epoch": 0.07, "percentage": 7.35, "elapsed_time": "0:07:53", "remaining_time": "1:39:23"}
+{"current_steps": 10, "total_steps": 68, "loss": 1.0736, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00018951632913550626, "epoch": 0.15, "percentage": 14.71, "elapsed_time": "0:15:47", "remaining_time": "1:31:34"}
+{"current_steps": 15, "total_steps": 68, "loss": 1.0295, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00017693339709828792, "epoch": 0.22, "percentage": 22.06, "elapsed_time": "0:23:43", "remaining_time": "1:23:50"}
+{"current_steps": 20, "total_steps": 68, "loss": 1.0088, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016026346363792567, "epoch": 0.29, "percentage": 29.41, "elapsed_time": "0:31:40", "remaining_time": "1:16:00"}
+{"current_steps": 25, "total_steps": 68, "loss": 0.9961, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00014039210048718949, "epoch": 0.36, "percentage": 36.76, "elapsed_time": "0:39:35", "remaining_time": "1:08:05"}
+{"current_steps": 30, "total_steps": 68, "loss": 0.9801, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00011837495178165706, "epoch": 0.44, "percentage": 44.12, "elapsed_time": "0:47:32", "remaining_time": "1:00:12"}
+{"current_steps": 35, "total_steps": 68, "loss": 0.9603, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.538165413542607e-05, "epoch": 0.51, "percentage": 51.47, "elapsed_time": "0:55:26", "remaining_time": "0:52:16"}
+{"current_steps": 40, "total_steps": 68, "loss": 0.9647, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.263370099279172e-05, "epoch": 0.58, "percentage": 58.82, "elapsed_time": "1:03:21", "remaining_time": "0:44:21"}
+{"current_steps": 45, "total_steps": 68, "loss": 0.9355, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.1339552143314384e-05, "epoch": 0.65, "percentage": 66.18, "elapsed_time": "1:11:18", "remaining_time": "0:36:26"}
+{"current_steps": 50, "total_steps": 68, "loss": 0.9217, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.263043563534428e-05, "epoch": 0.73, "percentage": 73.53, "elapsed_time": "1:19:14", "remaining_time": "0:28:31"}
+{"current_steps": 55, "total_steps": 68, "loss": 0.9623, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.750025254016978e-05, "epoch": 0.8, "percentage": 80.88, "elapsed_time": "1:27:10", "remaining_time": "0:20:36"}
+{"current_steps": 60, "total_steps": 68, "loss": 0.9369, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.75277705956443e-06, "epoch": 0.87, "percentage": 88.24, "elapsed_time": "1:35:05", "remaining_time": "0:12:40"}
+{"current_steps": 65, "total_steps": 68, "loss": 0.9075, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.589569124794916e-07, "epoch": 0.95, "percentage": 95.59, "elapsed_time": "1:42:59", "remaining_time": "0:04:45"}
+{"current_steps": 68, "total_steps": 68, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.99, "percentage": 100.0, "elapsed_time": "1:47:44", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9890909090909091,
+  "eval_steps": 500,
+  "global_step": 68,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0001973438054360693,
+      "loss": 1.1721,
+      "step": 5
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00018951632913550626,
+      "loss": 1.0736,
+      "step": 10
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00017693339709828792,
+      "loss": 1.0295,
+      "step": 15
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00016026346363792567,
+      "loss": 1.0088,
+      "step": 20
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00014039210048718949,
+      "loss": 0.9961,
+      "step": 25
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00011837495178165706,
+      "loss": 0.9801,
+      "step": 30
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.538165413542607e-05,
+      "loss": 0.9603,
+      "step": 35
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.263370099279172e-05,
+      "loss": 0.9647,
+      "step": 40
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.1339552143314384e-05,
+      "loss": 0.9355,
+      "step": 45
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.263043563534428e-05,
+      "loss": 0.9217,
+      "step": 50
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.750025254016978e-05,
+      "loss": 0.9623,
+      "step": 55
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 6.75277705956443e-06,
+      "loss": 0.9369,
+      "step": 60
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 9.589569124794916e-07,
+      "loss": 0.9075,
+      "step": 65
+    },
+    {
+      "epoch": 0.99,
+      "step": 68,
+      "total_flos": 9.5110421903573e+16,
+      "train_loss": 0.9853932401713204,
+      "train_runtime": 6464.5656,
+      "train_samples_per_second": 0.68,
+      "train_steps_per_second": 0.011
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 68,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 9.5110421903573e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72932adf16bc812d753a5b9e36a3df342abc66d9f0fd42f44cefdd096187bc55
+size 4920