End of training

README.md

@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: tokyotech-llm/Swallow-MS-7b-v0.1
+datasets:
+- generator
+model-index:
+- name: Mistral-7b-sft-lora-ha-v1.0_cleaned
+  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. -->
+
+# Mistral-7b-sft-lora-ha-v1.0_cleaned
+
+This model is a fine-tuned version of [tokyotech-llm/Swallow-MS-7b-v0.1](https://huggingface.co/tokyotech-llm/Swallow-MS-7b-v0.1) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2119
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.4836        | 1.0   | 189  | 1.2482          |
+| 1.2209        | 2.0   | 378  | 1.2224          |
+| 1.1941        | 3.0   | 567  | 1.2139          |
+| 1.1819        | 4.0   | 756  | 1.2119          |
+| 1.1787        | 5.0   | 945  | 1.2119          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "tokyotech-llm/Swallow-MS-7b-v0.1",
+  "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": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "lm_head",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "q_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 sha256:4caaf548e38f24fe417b8228035dcf5dadad4a7d19a88b10d078c7238b36f956
+size 393371984

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 6.657716927594496e+17,
+    "train_loss": 1.2518653021918402,
+    "train_runtime": 4827.6756,
+    "train_samples_per_second": 1.564,
+    "train_steps_per_second": 0.196
+}

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 sha256:6239e68e91d052426ceac4b17aadca42c34f5b2067caee6b67d42105742c1f16
+size 903208

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif false == true and not '<<SYS>>' in messages[0]['content'] %}{% set loop_messages = messages %}{% set system_message = 'あなたは誠実で優秀な日本人のアシスタントです。' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{{ bos_token }}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\n' + system_message + '\n<</SYS>>\n\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + content.strip() + ' [/INST] ' }}{% elif message['role'] == 'system' %}{{ '<<SYS>>\n' + content.strip() + '\n<</SYS>>\n\n' }}{% elif message['role'] == 'assistant' %}{{ ''  + content.strip() + '' + eos_token }}{% endif %}{% 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 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 6.657716927594496e+17,
+    "train_loss": 1.2518653021918402,
+    "train_runtime": 4827.6756,
+    "train_samples_per_second": 1.564,
+    "train_steps_per_second": 0.196
+}

trainer_state.json

@@ -0,0 +1,105 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 945,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.84375,
+      "learning_rate": 1.8805243942587e-05,
+      "loss": 1.4836,
+      "step": 189
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.248240351676941,
+      "eval_runtime": 14.7272,
+      "eval_samples_per_second": 5.364,
+      "eval_steps_per_second": 0.679,
+      "step": 189
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.98046875,
+      "learning_rate": 1.4032141389483648e-05,
+      "loss": 1.2209,
+      "step": 378
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.2223888635635376,
+      "eval_runtime": 14.6831,
+      "eval_samples_per_second": 5.38,
+      "eval_steps_per_second": 0.681,
+      "step": 378
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.0703125,
+      "learning_rate": 7.555868193598188e-06,
+      "loss": 1.1941,
+      "step": 567
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.2139047384262085,
+      "eval_runtime": 14.7087,
+      "eval_samples_per_second": 5.371,
+      "eval_steps_per_second": 0.68,
+      "step": 567
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.0078125,
+      "learning_rate": 2.111992708420646e-06,
+      "loss": 1.1819,
+      "step": 756
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.2119375467300415,
+      "eval_runtime": 14.6929,
+      "eval_samples_per_second": 5.377,
+      "eval_steps_per_second": 0.681,
+      "step": 756
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.125,
+      "learning_rate": 0.0,
+      "loss": 1.1787,
+      "step": 945
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.2118842601776123,
+      "eval_runtime": 14.7081,
+      "eval_samples_per_second": 5.371,
+      "eval_steps_per_second": 0.68,
+      "step": 945
+    },
+    {
+      "epoch": 5.0,
+      "step": 945,
+      "total_flos": 6.657716927594496e+17,
+      "train_loss": 1.2518653021918402,
+      "train_runtime": 4827.6756,
+      "train_samples_per_second": 1.564,
+      "train_steps_per_second": 0.196
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 945,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 6.657716927594496e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4cdba8b622c8fb66feb04920c4814ed75cb101c245e97d697b740adc3c2bf3a
+size 5048