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_2
+  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_2
+
+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 themesjson 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: 30.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.9.0
+- Transformers 4.38.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "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": [
+    "v_proj",
+    "q_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:e5de54e2c502242fa8e5e0f0acd72ce5d39e3716e301006ccae8ac8fcf7a7de2
+size 13648432

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 20.0,
+    "train_loss": 0.48743839263916017,
+    "train_runtime": 1116.6347,
+    "train_samples_per_second": 1.263,
+    "train_steps_per_second": 0.027
+}

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 +1,46 @@
+{
+  "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 system_message = messages[0]['content'] %}{% endif %}{{ '<s>' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '[INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% 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": 0.48743839263916017,
+    "train_runtime": 1116.6347,
+    "train_samples_per_second": 1.263,
+    "train_steps_per_second": 0.027
+}

trainer_log.jsonl

@@ -0,0 +1,7 @@
+{"current_steps": 5, "total_steps": 30, "loss": 0.5792, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00018660254037844388, "epoch": 3.0, "percentage": 16.67, "elapsed_time": "0:02:41", "remaining_time": "0:13:26"}
+{"current_steps": 10, "total_steps": 30, "loss": 0.6021, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00015000000000000001, "epoch": 6.67, "percentage": 33.33, "elapsed_time": "0:06:06", "remaining_time": "0:12:12"}
+{"current_steps": 15, "total_steps": 30, "loss": 0.4859, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "0:09:14", "remaining_time": "0:09:14"}
+{"current_steps": 20, "total_steps": 30, "loss": 0.4403, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000000000000002e-05, "epoch": 13.33, "percentage": 66.67, "elapsed_time": "0:12:21", "remaining_time": "0:06:10"}
+{"current_steps": 25, "total_steps": 30, "loss": 0.4547, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.339745962155613e-05, "epoch": 17.0, "percentage": 83.33, "elapsed_time": "0:15:48", "remaining_time": "0:03:09"}
+{"current_steps": 30, "total_steps": 30, "loss": 0.3624, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:18:36", "remaining_time": "0:00:00"}
+{"current_steps": 30, "total_steps": 30, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:18:36", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.0,
+  "eval_steps": 500,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.15062181651592255,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 0.5792,
+      "step": 5
+    },
+    {
+      "epoch": 6.67,
+      "grad_norm": 0.32858145236968994,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.6021,
+      "step": 10
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.3023599088191986,
+      "learning_rate": 0.0001,
+      "loss": 0.4859,
+      "step": 15
+    },
+    {
+      "epoch": 13.33,
+      "grad_norm": 0.20432211458683014,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.4403,
+      "step": 20
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 0.3563392162322998,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.4547,
+      "step": 25
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.35112833976745605,
+      "learning_rate": 0.0,
+      "loss": 0.3624,
+      "step": 30
+    },
+    {
+      "epoch": 20.0,
+      "step": 30,
+      "total_flos": 1.6995565288095744e+16,
+      "train_loss": 0.48743839263916017,
+      "train_runtime": 1116.6347,
+      "train_samples_per_second": 1.263,
+      "train_steps_per_second": 0.027
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 30,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 100,
+  "total_flos": 1.6995565288095744e+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 sha256:7e9cbafe8fa0455627780b373a009eec32b1e23af0d8772fdfad517aaa8c2829
+size 5048