Upload 11 files

README.md

@@ -0,0 +1,61 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+model-index:
+- name: train_2024-02-01-10-50-39
+  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_2024-02-01-10-50-39
+
+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 wiki_demo dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.3668
+
+## 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-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 20.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.8.1
+- Transformers 4.37.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "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,
+  "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",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c4351ae9e640746fef40bbe9f306965f9bd1e8d15eaf1e4c29b32269c6b664d
+size 13648432

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 2.3668270111083984,
+    "eval_runtime": 1.9011,
+    "eval_samples_per_second": 2.104,
+    "eval_steps_per_second": 0.526,
+    "perplexity": 10.663503370230504,
+    "train_loss": 2.338414525985718,
+    "train_runtime": 453.0464,
+    "train_samples_per_second": 0.662,
+    "train_steps_per_second": 0.044
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 2.3668270111083984,
+    "eval_runtime": 1.9011,
+    "eval_samples_per_second": 2.104,
+    "eval_steps_per_second": 0.526,
+    "perplexity": 10.663503370230504
+}

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": 20.0,
+    "train_loss": 2.338414525985718,
+    "train_runtime": 453.0464,
+    "train_samples_per_second": 0.662,
+    "train_steps_per_second": 0.044
+}

trainer_log.jsonl

@@ -0,0 +1,6 @@
+{"current_steps": 5, "total_steps": 20, "loss": 2.4236, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.267766952966369e-05, "epoch": 5.0, "percentage": 25.0, "elapsed_time": "0:01:53", "remaining_time": "0:05:41"}
+{"current_steps": 10, "total_steps": 20, "loss": 2.3423, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5e-05, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "0:03:46", "remaining_time": "0:03:46"}
+{"current_steps": 15, "total_steps": 20, "loss": 2.302, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.3223304703363135e-06, "epoch": 15.0, "percentage": 75.0, "elapsed_time": "0:05:39", "remaining_time": "0:01:53"}
+{"current_steps": 20, "total_steps": 20, "loss": 2.2859, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:07:33", "remaining_time": "0:00:00"}
+{"current_steps": 20, "total_steps": 20, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:07:33", "remaining_time": "0:00:00"}
+{"current_steps": 1, "total_steps": 1, "loss": null, "eval_loss": 2.3668270111083984, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:07:34", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.0,
+  "eval_steps": 100,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 2.4236,
+      "step": 5
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 2.5e-05,
+      "loss": 2.3423,
+      "step": 10
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 2.302,
+      "step": 15
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 0.0,
+      "loss": 2.2859,
+      "step": 20
+    },
+    {
+      "epoch": 20.0,
+      "step": 20,
+      "total_flos": 3.87232947634176e+16,
+      "train_loss": 2.338414525985718,
+      "train_runtime": 453.0464,
+      "train_samples_per_second": 0.662,
+      "train_steps_per_second": 0.044
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 20,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 100,
+  "total_flos": 3.87232947634176e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}